© 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. 7-RESID-POST-AA
    11. 113392
    Prev
    Next
    INDEX
    Explanations

    civic/administrative locations/roles

    np_max-act · gemini-2.0-flash

    mentions of people in institutional roles or job titles (e.g., staff, board members, officers, teachers, residents).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Friday
    -0.06
     LL
    -0.06
    AVE
    -0.06
    .pad
    -0.06
     Houston
    -0.06
     people
    -0.06
     tomb
    -0.06
     sở
    -0.06
    ierarchical
    -0.06
     دوست
    -0.06
    POSITIVE LOGITS
     gigg
    0.07
    ListItem
    0.06
    افته
    0.06
    OrFail
    0.06
    ):
    0.06
     propagated
    0.06
    vern
    0.06
    (details
    0.06
    альна
    0.06
     Kent
    0.06
    Activations Density 0.288%

    No Known Activations