© 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. 43353
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    This neuron never activates—it does not respond to any tokens.

    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
     GX
    -0.07
    metadata
    -0.06
    uur
    -0.06
     expressions
    -0.06
     trail
    -0.06
    írk
    -0.06
     Mask
    -0.06
    faq
    -0.06
    図
    -0.06
    |()↵
    -0.06
    POSITIVE LOGITS
     dealings
    0.07
    veedor
    0.07
     ت
    0.06
     zipcode
    0.06
     Romero
    0.06
     Но
    0.06
     ای
    0.06
    comments
    0.06
    .setVerticalGroup
    0.06
    ными
    0.06
    Activations Density 0.003%

    No Known Activations