© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6338
    Prev
    Next
    INDEX
    Explanations

    current events

    np_max-act · gemini-2.0-flash

    references to legislative actions and political discussions regarding gun control.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The main thing this neuron does is pick up on formal political or legal terminology—mentions of government bodies, legislative actions, and judicial processes.

    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
    (work
    -0.07
    됩니다
    -0.07
    _gb
    -0.07
     urlencode
    -0.07
     ca
    -0.06
     ми
    -0.06
     Bren
    -0.06
     Tf
    -0.06
     exercised
    -0.06
    inha
    -0.06
    POSITIVE LOGITS
    ffect
    0.06
    だけ
    0.06
     millions
    0.06
     جمله
    0.06
     dur
    0.06
    ulner
    0.06
    ổng
    0.06
     precip
    0.06
    降
    0.06
     \
↵
    0.06
    Activations Density 0.188%

    No Known Activations