© 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. 35935
    Prev
    Next
    INDEX
    Explanations

    code/web development

    np_max-act · gemini-2.0-flash

    tokens used for model/control metadata (e.g., end-of-text/header markers like <|eot_id|>)

    oai_token-act-pair · gpt-5-miniTriggered 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
     yine
    -0.08
    реб
    -0.07
     parametros
    -0.07
    oshi
    -0.07
    high
    -0.07
     Fortress
    -0.07
     heav
    -0.07
     trapping
    -0.06
    Wild
    -0.06
     parti
    -0.06
    POSITIVE LOGITS
    ें।↵
    0.07
    .).
    0.07
    ._↵↵
    0.07
    ).↵↵↵
    0.07
    .(*
    0.07
    .Att
    0.06
    "].
    0.06
    .Current
    0.06
     суб
    0.06
    .↵↵↵
    0.06
    Activations Density 0.094%

    No Known Activations