© 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. 68915
    Prev
    Next
    INDEX
    Explanations

    wine

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of alcoholic beverages and drink lists (e.g., wine, cocktails, beer).

    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
     >/
    -0.07
     {}).
    -0.06
     examples
    -0.06
    电话
    -0.06
    (se
    -0.06
     fileInfo
    -0.06
    gal
    -0.06
    .mem
    -0.06
     chu
    -0.06
    /Product
    -0.06
    POSITIVE LOGITS
    lasses
    0.07
    _WRONG
    0.06
     خارجی
    0.06
     cigaret
    0.06
     datové
    0.06
     Hook
    0.06
    enství
    0.06
    sdale
    0.06
    ουργ
    0.06
    ocurrency
    0.06
    Activations Density 0.012%

    No Known Activations