© 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
    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. 99261
    Prev
    Next
    INDEX
    Explanations

    colons

    np_max-act · gemini-2.0-flash

    The token marking the end of a header block (the <|end_header_id|> / role-header boundary before assistant responses).

    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
     nozzle
    -0.07
     Thornton
    -0.07
     Castillo
    -0.06
     сказ
    -0.06
     Arap
    -0.06
    029
    -0.06
     fuzz
    -0.06
     普
    -0.06
    経
    -0.06
     παρ
    -0.06
    POSITIVE LOGITS
     nä
    0.07
    _polygon
    0.07
    (Cl
    0.07
    ;↵↵
    0.06
     Divide
    0.06
     sigu
    0.06
     луч
    0.06
    )"↵
    0.06
    )"↵↵
    0.06
                 ↵
    0.06
    Activations Density 0.127%

    No Known Activations