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

    Neuronpedia

    APICircuit 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. 111144
    Prev
    Next
    INDEX
    Explanations

    services and processes

    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
    Iss
    -0.07
     undefeated
    -0.07
     brawl
    -0.06
     zus
    -0.06
     trembling
    -0.06
     when
    -0.06
    ンジ
    -0.06
    ažd
    -0.06
     Melania
    -0.06
    Ultimately
    -0.06
    POSITIVE LOGITS
    анням
    0.06
    .values
    0.06
    (load
    0.06
    _drop
    0.06
    .ViewModel
    0.06
    .read
    0.06
    _FULL
    0.06
    ->___
    0.06
     onlar
    0.06
    LANGUAGE
    0.06
    Activations Density 0.076%

    No Known Activations