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. 11-RESID-POST-AA
    6. 76212
    Prev
    Next
    INDEX
    Explanations

    research publications

    np_max-act · gemini-2.0-flash

    references to trauma and surgical procedures related to patient care in both civilian and military contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cait
    -0.07
     knih
    -0.07
     Lud
    -0.07
     certifications
    -0.06
    .strptime
    -0.06
     Michael
    -0.06
    /history
    -0.06
    ův
    -0.06
    자가
    -0.06
    áže
    -0.06
    POSITIVE LOGITS
    -gray
    0.07
     UNS
    0.06
     fen
    0.06
     dividends
    0.06
     consequential
    0.06
     大
    0.06
    .quiz
    0.06
    _WRAP
    0.06
     Discount
    0.06
     Clara
    0.06
    Activations Density 0.063%

    No Known Activations