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. 53825
    Prev
    Next
    INDEX
    Explanations

    from

    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
    /he
    -0.07
     lekker
    -0.06
    ICH
    -0.06
     справи
    -0.06
     Surge
    -0.06
     genu
    -0.06
    ้เก
    -0.06
    toContain
    -0.06
    qty
    -0.06
    optgroup
    -0.06
    POSITIVE LOGITS
     simple
    0.07
     diss
    0.07
     Seconds
    0.06
     mouth
    0.06
    _AUTO
    0.06
     landing
    0.06
    า�
    0.06
    纪
    0.06
     classes
    0.06
     craw
    0.06
    Activations Density 0.003%

    No Known Activations