© 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. 73610
    Prev
    Next
    INDEX
    Explanations

    Surgical flaps

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “flap” (as in surgical flaps).

    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
    weakSelf
    -0.07
     paci
    -0.07
    (MediaType
    -0.06
     Memory
    -0.06
    RenderWindow
    -0.06
    .ConnectionString
    -0.06
    .address
    -0.06
    .hits
    -0.06
     θέ
    -0.06
     hostname
    -0.06
    POSITIVE LOGITS
     flap
    0.09
    sa
    0.07
     Pam
    0.07
    ifs
    0.07
    Flip
    0.07
     Detailed
    0.07
    +p
    0.07
     Sap
    0.07
    เผ
    0.07
    wrap
    0.06
    Activations Density 0.001%

    No Known Activations