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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 27295
    Prev
    Next
    INDEX
    Explanations

    cooking, taste, seasonings

    np_max-act · gemini-2.0-flash

    instructions or action verbs in cooking steps (e.g., tasting/checking/stirring).

    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
    巨
    -0.06
    Creature
    -0.06
    alous
    -0.06
     PROCUREMENT
    -0.06
     diffusion
    -0.06
    ीय
    -0.06
     exponential
    -0.06
     ль
    -0.06
    productive
    -0.06
     phủ
    -0.06
    POSITIVE LOGITS
    ('./
    0.06
    .Ph
    0.06
    ("./
    0.06
    \L
    0.06
    ');?></
    0.06
    ?v
    0.06
    ?></
    0.06
    并不
    0.06
    ;"><?
    0.06
    _entity
    0.06
    Activations Density 0.034%

    No Known Activations