© 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. 11-RESID-POST-AA
    11. 92053
    Prev
    Next
    INDEX
    Explanations

    static

    np_max-act · gemini-2.0-flash

    This neuron detects C declarations or definitions introduced by the storage‐class keyword “static.”

    oai_token-act-pair · o4-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
    Sou
    -0.06
    presso
    -0.06
     barrier
    -0.06
    ;?>↵
    -0.06
    .file
    -0.06
    leton
    -0.06
     problem
    -0.06
     burial
    -0.06
     reinterpret
    -0.06
     Bride
    -0.06
    POSITIVE LOGITS
    setEnabled
    0.08
    ความค
    0.07
    ческие
    0.07
    .setEnabled
    0.07
     shouts
    0.07
     youthful
    0.07
    alignment
    0.07
    stay
    0.06
    neo
    0.06
    caster
    0.06
    Activations Density 0.002%

    No Known Activations