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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 104157
    Prev
    Next
    INDEX
    Explanations

    .C

    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_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
    walk
    -0.07
     Humanity
    -0.07
    Expected
    -0.07
     economies
    -0.06
    .Positive
    -0.06
    (entities
    -0.06
     humanities
    -0.06
    iences
    -0.06
    _form
    -0.06
    smith
    -0.06
    POSITIVE LOGITS
    >r
    0.07
    _caption
    0.06
    .</
    0.06
     рецепт
    0.06
    -runtime
    0.06
    ,</
    0.06
     cro
    0.06
     ска
    0.06
    ?-
    0.06
    VEC
    0.06
    Activations Density 0.004%

    No Known Activations