© 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. 118953
    Prev
    Next
    INDEX
    Explanations

    NST

    np_max-act · gemini-2.0-flash

    structural chat-format delimiters, particularly header markers and end-of-turn boundaries.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    _attached
    -0.07
    �
    -0.07
     anybody
    -0.07
     meant
    -0.06
     명
    -0.06
     annoy
    -0.06
     čtyři
    -0.06
    重点
    -0.06
     tud
    -0.06
    someone
    -0.06
    POSITIVE LOGITS
    .changed
    0.06
     Frage
    0.06
    uje
    0.06
    ीएम
    0.06
     TRADE
    0.06
    (vertex
    0.06
    lectual
    0.06
    О
    0.06
    ोस
    0.06
    WK
    0.06
    Activations Density 0.190%

    No Known Activations