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. 59302
    Prev
    Next
    INDEX
    Explanations

    php

    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
    .title
    -0.07
     SIX
    -0.07
     DOJ
    -0.07
    Patrick
    -0.07
     Entries
    -0.06
     Gazette
    -0.06
    .Movie
    -0.06
    Separ
    -0.06
    ладу
    -0.06
    _Element
    -0.06
    POSITIVE LOGITS
    oplevel
    0.07
    aged
    0.07
    ht
    0.07
    upid
    0.07
    ologically
    0.07
    iosper
    0.06
    _norm
    0.06
     предус
    0.06
    swing
    0.06
    amines
    0.06
    Activations Density 0.003%

    No Known Activations