© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30683
    Prev
    Next
    INDEX
    Explanations

    music albums

    np_max-act · gemini-2.0-flash

    The neuron fires on upbeat, promotional descriptive language—especially evaluative adjectives and similes—used in album/release blurbs.

    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
    .FloatField
    -0.07
     washer
    -0.06
    lepší
    -0.06
    ang
    -0.06
    фра
    -0.06
    enant
    -0.06
    たい
    -0.06
     Арх
    -0.06
    ChildIndex
    -0.06
    ANG
    -0.06
    POSITIVE LOGITS
    (HWND
    0.07
    Mappings
    0.06
     '!
    0.06
     Traff
    0.06
    unu
    0.06
     '(
    0.06
     Opposition
    0.06
     lexical
    0.06
     latter
    0.06
    always
    0.06
    Activations Density 0.022%

    No Known Activations