© 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. 125927
    Prev
    Next
    INDEX
    Explanations

    medical practitioners and papers

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of a specific proper name (in this case “Newman”).

    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
    .gener
    -0.07
     annunci
    -0.06
    .Combine
    -0.06
    _public
    -0.06
    华
    -0.06
    school
    -0.06
    ской
    -0.06
    	fields
    -0.06
     Urs
    -0.06
    /github
    -0.06
    POSITIVE LOGITS
     Auburn
    0.07
    leared
    0.07
     creep
    0.07
     उन
    0.06
     Weiter
    0.06
     conceal
    0.06
     Pastor
    0.06
    把
    0.06
    nels
    0.06
     &↵
    0.06
    Activations Density 0.013%

    No Known Activations