© 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. 91630
    Prev
    Next
    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of file input/output operations (e.g., opening, reading, writing files).

    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
    _rgba
    -0.07
     tanker
    -0.07
     notices
    -0.06
     emojis
    -0.06
    χα
    -0.06
    .rating
    -0.06
    amaha
    -0.06
     월세
    -0.06
    .button
    -0.06
     rsp
    -0.06
    POSITIVE LOGITS
     дальней
    0.07
    -publish
    0.07
     satisfy
    0.06
     advisable
    0.06
     حالة
    0.06
    lining
    0.06
     payable
    0.06
    cheduled
    0.06
    -direct
    0.06
     hac
    0.06
    Activations Density 0.055%

    No Known Activations