Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 45377
    Prev
    Next
    INDEX
    Explanations

    unable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     april
    -0.06
     Nice
    -0.06
    ỏ
    -0.06
    :model
    -0.06
     افزایش
    -0.06
     basement
    -0.06
     coast
    -0.06
    Factor
    -0.06
     Rome
    -0.06
    args
    -0.06
    POSITIVE LOGITS
    T
    0.07
    Uint
    0.07
    .btnExit
    0.07
    [
    0.07
    TC
    0.07
     дви
    0.07
     LinearGradient
    0.06
    .Handled
    0.06
    _subtype
    0.06
     Grab
    0.06
    Activations Density 0.009%

    No Known Activations