© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58002
    Prev
    Next
    INDEX
    Explanations

    correlation coefficient

    np_max-act · gemini-2.0-flash

    scientific terms and phrases related to measurements and methods in environmental and health research.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on mentions of statistical model‐fitting metrics (e.g. R², correlation coefficients, regression equations, “model fit,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AP
    -0.06
     CallingConvention
    -0.06
     txn
    -0.06
    .mx
    -0.06
    adows
    -0.06
    .ToUpper
    -0.06
    .array
    -0.06
    .safe
    -0.06
     믿
    -0.06
     jente
    -0.06
    POSITIVE LOGITS
    -str
    0.07
     cof
    0.07
     organic
    0.07
    067
    0.06
     immigr
    0.06
     lowering
    0.06
     noses
    0.06
     involved
    0.06
     demonstrated
    0.06
     Psr
    0.06
    Activations Density 0.010%

    No Known Activations