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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19-RESID-POST-AA
    11. 9543
    Prev
    Next
    INDEX
    Explanations

    file

    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
    .WinForms
    -0.07
    -column
    -0.07
     dib
    -0.07
     Joi
    -0.06
     öyle
    -0.06
    たら
    -0.06
    /style
    -0.06
    Qualified
    -0.06
    seeing
    -0.06
     posit
    -0.06
    POSITIVE LOGITS
    (ir
    0.06
    tele
    0.06
     memorandum
    0.06
    _UNIFORM
    0.06
    .com
    0.06
    чим
    0.06
     Icelandic
    0.06
    REAK
    0.06
    쉬
    0.06
     troub
    0.06
    Activations Density 0.005%

    No Known Activations