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

    Neuronpedia

    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. 42818
    Prev
    Next
    INDEX
    Explanations

    Numerical lists

    np_max-act · gemini-2.0-flash

    The neuron activates on floating-point numeric literals (decimal numbers) in code.

    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
    _iteration
    -0.06
     deficiencies
    -0.06
    cir
    -0.06
    jsonData
    -0.06
    .addr
    -0.06
    slides
    -0.06
    омер
    -0.06
     başında
    -0.06
     raspberry
    -0.06
    otr
    -0.06
    POSITIVE LOGITS
    ulously
    0.06
    .Peek
    0.06
    UEL
    0.06
     cerr
    0.06
    ensual
    0.06
     العرب
    0.06
     Measures
    0.06
    avigate
    0.06
    tol
    0.06
     consuming
    0.06
    Activations Density 0.010%

    No Known Activations