© 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. 91669
    Prev
    Next
    INDEX
    Explanations

    responses

    np_max-act · gemini-2.0-flash

    The neuron fires on discussion of returning or constructing HTTP responses (especially JSON responses) in web-framework code.

    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
     popover
    -0.07
    ότητα
    -0.07
    buy
    -0.06
     Demand
    -0.06
    -service
    -0.06
     Walk
    -0.06
     Pay
    -0.06
    Bed
    -0.06
     елек
    -0.06
     CancellationToken
    -0.06
    POSITIVE LOGITS
    _IDX
    0.07
    ’est
    0.06
     nouvelle
    0.06
     fecha
    0.06
    'est
    0.06
    슬
    0.06
    .xx
    0.06
     imposed
    0.06
     varieties
    0.06
     ++
    0.06
    Activations Density 0.037%

    No Known Activations