© 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. 68995
    Prev
    Next
    INDEX
    Explanations

    Trying something

    np_max-act · gemini-2.0-flash

    This neuron fires on informal expressions of trying something out—especially the “give X a whirl/try” phrasing.

    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
     collagen
    -0.06
    いで
    -0.06
    _overlap
    -0.06
     magnet
    -0.06
     Stuart
    -0.05
    Airport
    -0.05
     crystall
    -0.05
    Hy
    -0.05
     scholarly
    -0.05
     ell
    -0.05
    POSITIVE LOGITS
     tackle
    0.08
    ्पन
    0.08
    lowest
    0.07
     retal
    0.07
    ина
    0.07
    $conn
    0.06
     danh
    0.06
     характ
    0.06
    discussion
    0.06
    gaben
    0.06
    Activations Density 0.017%

    No Known Activations