© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 27599
    Prev
    Next
    INDEX
    Explanations

    product/protein

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     magnets
    -0.06
    _sigma
    -0.06
    raph
    -0.06
     Hastings
    -0.06
     fileprivate
    -0.06
    feito
    -0.06
    _IDX
    -0.06
    伯
    -0.06
    ube
    -0.06
    .tx
    -0.06
    POSITIVE LOGITS
     Nhưng
    0.07
     تحلیل
    0.06
     případně
    0.06
    ).↵↵↵↵
    0.06
     그래서
    0.06
    "})↵
    0.06
     epidemi
    0.06
     Insecta
    0.06
    (delegate
    0.06
    )},↵
    0.06
    Activations Density 0.033%

    No Known Activations