© 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. 11-RESID-POST-AA
    6. 128866
    Prev
    Next
    INDEX
    Explanations

    Awards

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of awards or honors (e.g., “Awards,” “Award,” winning recognitions).

    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
     enrichment
    -0.07
     Constant
    -0.07
    rz
    -0.07
    ,ll
    -0.06
    finity
    -0.06
    933
    -0.06
    throw
    -0.06
    ADR
    -0.06
    .getLogin
    -0.06
     Professional
    -0.06
    POSITIVE LOGITS
    Navigator
    0.07
    科学
    0.07
    */}↵
    0.07
     آسیاب
    0.06
    _DETAILS
    0.06
    ái
    0.06
     subtle
    0.06
     хлоп
    0.06
    ümüzde
    0.06
    _foreign
    0.06
    Activations Density 0.014%

    No Known Activations