© 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. 85739
    Prev
    Next
    INDEX
    Explanations

    HTTP status codes

    np_max-act · gemini-2.0-flash

    This neuron activates on sequences of three-digit HTTP status codes (e.g. “503”, “502”).

    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
    udur
    -0.07
    erialize
    -0.06
    fill
    -0.06
     roast
    -0.06
    ुड
    -0.06
     trained
    -0.06
    getter
    -0.06
     training
    -0.06
    .Add
    -0.06
    .handleClick
    -0.06
    POSITIVE LOGITS
    (block
    0.07
    ↵
    0.07
    人物
    0.07
    .Fecha
    0.06
     pillar
    0.06
    Scaled
    0.06
     Thiết
    0.06
     �
    0.06
     тяж
    0.06
    parsed
    0.06
    Activations Density 0.002%

    No Known Activations