Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 128236
    Prev
    Next
    INDEX
    Explanations

    colons

    np_max-act · gemini-2.0-flash

    tokens used for conversation metadata and structure (header/role markers, timestamps, and other control 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_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
    리즈
    -0.08
    ,T
    -0.07
     solidarity
    -0.07
    	dst
    -0.06
    _DRAW
    -0.06
    名稱
    -0.06
     wage
    -0.06
     rebell
    -0.06
    without
    -0.06
    —who
    -0.06
    POSITIVE LOGITS
     лекар
    0.06
     националь
    0.06
     множе
    0.06
    ề
    0.06
     مرتبط
    0.06
    iền
    0.06
     зобов
    0.06
    ">'
    0.06
     thuis
    0.06
     Oral
    0.06
    Activations Density 0.330%

    No Known Activations