© 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. 78796
    Prev
    Next
    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash

    phrases referring to anatomy, clinical findings, or medical orders in clinical/medical notes.

    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
    ウォ
    -0.08
    unistd
    -0.06
     kings
    -0.06
    ลอง
    -0.06
    .ExecuteNonQuery
    -0.06
    ouncer
    -0.06
    mesini
    -0.06
    TABLE
    -0.06
    py
    -0.06
     inhibition
    -0.06
    POSITIVE LOGITS
    (Paint
    0.06
    'acc
    0.06
    .addTarget
    0.06
     Russian
    0.06
    (solution
    0.06
     "{$
    0.06
     Face
    0.06
    .notes
    0.06
    ولو
    0.06
     Dive
    0.06
    Activations Density 0.701%

    No Known Activations