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. 54379
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    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
    ++);↵
    -0.07
     해야
    -0.07
     "");↵
    -0.07
    _ra
    -0.07
     який
    -0.06
    _pa
    -0.06
    _ne
    -0.06
    licable
    -0.06
    .z
    -0.06
    _ext
    -0.06
    POSITIVE LOGITS
     numeral
    0.07
     optimize
    0.07
     INITIAL
    0.07
     возможности
    0.07
     beta
    0.07
     nurturing
    0.07
    .ALIGN
    0.06
    .console
    0.06
     laptops
    0.06
    보고
    0.06
    Activations Density 0.003%

    No Known Activations