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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 21264
    Prev
    Next
    INDEX
    Explanations

    Code/Technical writing

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.08
     présent
    -0.07
    -insert
    -0.07
     وما
    -0.07
    .rar
    -0.06
     Ottoman
    -0.06
     ADDR
    -0.06
     bre
    -0.06
     dentist
    -0.06
     purse
    -0.06
    POSITIVE LOGITS
    인을
    0.06
    Json
    0.06
     Diabetes
    0.06
     directory
    0.06
    (animated
    0.06
     may
    0.06
     jsonResponse
    0.06
    (px
    0.06
    /components
    0.06
     restless
    0.06
    Activations Density 0.000%

    No Known Activations