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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 86363
    Prev
    Next
    INDEX
    Explanations

    t

    np_max-act · gemini-2.0-flash

    tokens containing numbers (digits) — e.g., dates, version numbers, numeric literals and similar numeric tokens.

    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_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
     ब
    -0.07
    _OPER
    -0.07
     Verb
    -0.07
     IOError
    -0.07
     quatre
    -0.07
    プロ
    -0.07
    Descriptors
    -0.07
    �
    -0.07
     ici
    -0.07
     Font
    -0.07
    POSITIVE LOGITS
    Ă
    0.06
     刘
    0.06
    stitution
    0.06
    koliv
    0.06
    ')↵
    0.06
    ustr
    0.06
    .)↵↵↵↵
    0.06
    post
    0.06
    んで
    0.06
    ↵    ↵    ↵
    0.06
    Activations Density 0.359%

    No Known Activations