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. 127283
    Prev
    Next
    INDEX
    Explanations

    general text

    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
     рас
    -0.06
    香港
    -0.06
    _FRAME
    -0.06
    --;
    -0.06
    <l
    -0.06
    &q
    -0.06
    (kernel
    -0.06
    [parent
    -0.06
     pursuant
    -0.06
     daň
    -0.06
    POSITIVE LOGITS
     allocate
    0.07
     misconduct
    0.07
     Win
    0.07
    IGHT
    0.07
     lightweight
    0.07
    Device
    0.07
     svm
    0.07
     Memo
    0.06
     cumbersome
    0.06
     preserve
    0.06
    Activations Density 0.000%

    No Known Activations