© 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. 126748
    Prev
    Next
    INDEX
    Explanations

    elections

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of legislative bodies and election contexts (e.g. “House of Representatives,” “congressional,” “Lok Sabha,” “parliamentary”).

    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
    neum
    -0.07
    sport
    -0.07
    イス
    -0.07
     обст
    -0.07
    üns
    -0.07
    );↵↵↵
    -0.06
    IFE
    -0.06
    .coords
    -0.06
    aths
    -0.06
     Leeds
    -0.06
    POSITIVE LOGITS
    ，加
    0.07
    285
    0.06
    __((
    0.06
     Takım
    0.06
    なが
    0.06
     Administrative
    0.06
    yclopedia
    0.06
     carve
    0.06
    xBA
    0.06
     ba
    0.06
    Activations Density 0.008%

    No Known Activations