© 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. 44211
    Prev
    Next
    INDEX
    Explanations

    News events

    np_max-act · gemini-2.0-flash

    The neuron responds to capitalized named entities and news‐style metadata—e.g. proper nouns, organizations, locations, bylines, and press credits.

    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
     organising
    -0.07
     europé
    -0.07
     Oscars
    -0.07
    acias
    -0.07
    áticas
    -0.06
     Curry
    -0.06
    興
    -0.06
     films
    -0.06
     europe
    -0.06
     China
    -0.06
    POSITIVE LOGITS
     Winnipeg
    0.07
     playoff
    0.07
    [:,
    0.07
     Canada
    0.07
    часно
    0.06
     Πο
    0.06
     lot
    0.06
     directional
    0.06
    (so
    0.06
     REAL
    0.06
    Activations Density 0.237%

    No Known Activations