© 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 EvalsExportsAPI 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. 56916
    Prev
    Next
    INDEX
    Explanations

    validity

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “validity” (and related methodological‐quality terms) in academic or forensic evaluation contexts.

    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
    tour
    -0.07
    environment
    -0.07
     місце
    -0.07
    azer
    -0.07
     merkez
    -0.07
    瀬
    -0.06
     mapa
    -0.06
     množství
    -0.06
     رسول
    -0.06
     přátel
    -0.06
    POSITIVE LOGITS
    jax
    0.08
     validity
    0.08
     valid
    0.07
    vation
    0.06
     levy
    0.06
    効
    0.06
    \Id
    0.06
    (tag
    0.06
    /welcome
    0.06
    )did
    0.06
    Activations Density 0.006%

    No Known Activations