© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90615
    Prev
    Next
    INDEX
    Explanations

    Harvard

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “Harvard.”

    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
    érieur
    -0.08
    _si
    -0.07
    ureka
    -0.07
    ).'
    -0.06
    宁
    -0.06
    -summary
    -0.06
    umbnail
    -0.06
    ?action
    -0.06
     Bang
    -0.06
     축
    -0.06
    POSITIVE LOGITS
     Harvard
    0.13
     marble
    0.08
     valve
    0.08
     Marble
    0.07
     gravel
    0.07
    Var
    0.07
     Valve
    0.07
    WAR
    0.07
    /MIT
    0.07
    ard
    0.07
    Activations Density 0.002%

    No Known Activations