Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84617
    Prev
    Next
    INDEX
    Explanations

    Digestion/intestines

    np_max-act · gemini-2.0-flash

    The neuron is triggered by mentions of specific regions of the intestine or gut (e.g. small intestine, large intestine, duodenum, hind gut).

    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
     enjoyment
    -0.07
    /products
    -0.07
    USTER
    -0.07
     agitation
    -0.07
    ejte
    -0.06
    EG
    -0.06
     Brushes
    -0.06
     BAD
    -0.06
    _hz
    -0.06
     TP
    -0.06
    POSITIVE LOGITS
    loggedIn
    0.06
    ỳ
    0.06
    ğına
    0.06
     ром
    0.06
     محدود
    0.06
     yılında
    0.06
    らない
    0.06
    moz
    0.06
     Claim
    0.06
    <Location
    0.06
    Activations Density 0.010%

    No Known Activations