© 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. 88090
    Prev
    Next
    INDEX
    Explanations

    Clothing details

    np_max-act · gemini-2.0-flash

    The neuron strongly responds to mentions of garment or product construction and hardware details—i.e. structural features and design elements in the description.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    descriptions of specific clothing items and their features.

    oai_token-act-pair · gpt-4o-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
     Lewis
    -0.06
    ľ
    -0.06
     dwar
    -0.06
     Keep
    -0.06
     Women
    -0.06
     Сов
    -0.06
    tasks
    -0.06
     decree
    -0.06
    _labels
    -0.06
     Jesus
    -0.06
    POSITIVE LOGITS
     renal
    0.08
    ignal
    0.07
     argc
    0.06
     ruta
    0.06
     ate
    0.06
    _IL
    0.06
     тот
    0.06
     satisf
    0.06
    уда
    0.06
    .Orientation
    0.06
    Activations Density 0.007%

    No Known Activations