© 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. 112241
    Prev
    Next
    INDEX
    Explanations

    blood vessels

    np_max-act · gemini-2.0-flash

    References to the artery's inner wall and its thickening or proliferative changes (neointimal/intimal hyperplasia).

    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
     발생
    -0.07
     Ibn
    -0.07
     jedoch
    -0.07
     majestic
    -0.06
     Edwin
    -0.06
    ْه
    -0.06
     obedient
    -0.06
     participants
    -0.06
     ImageButton
    -0.06
    (button
    -0.06
    POSITIVE LOGITS
     quicker
    0.06
    toThrow
    0.06
    พระ
    0.06
     MIME
    0.06
    isArray
    0.06
     zlib
    0.06
    BOVE
    0.06
    ста
    0.06
    \Log
    0.06
    _challenge
    0.06
    Activations Density 0.000%

    No Known Activations