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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-RESID-POST-AA
    6. 83195
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    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
    .mount
    -0.07
    RAD
    -0.06
    ALL
    -0.06
    ICODE
    -0.06
    ерб
    -0.06
    dden
    -0.06
    IDER
    -0.06
     seizure
    -0.06
    AMED
    -0.06
     unauthorized
    -0.06
    POSITIVE LOGITS
     allow
    0.06
    back
    0.06
    elect
    0.06
    _patches
    0.06
    Jonathan
    0.06
     craw
    0.06
    (T
    0.06
     practically
    0.06
    ,default
    0.06
    Allowed
    0.06
    Activations Density 0.019%

    No Known Activations