© 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. 109738
    Prev
    Next
    INDEX
    Explanations

    code and technical language

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “causes,” i.e. the explicit indicator of a causal relationship between two events.

    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
    _REGION
    -0.06
     прий
    -0.06
    اورپوینت
    -0.06
    .latest
    -0.06
     hairst
    -0.06
     discussed
    -0.06
    FunctionFlags
    -0.06
    bild
    -0.06
     تهران
    -0.06
    ToFit
    -0.06
    POSITIVE LOGITS
    :f
    0.07
     amy
    0.07
    nos
    0.07
     بی
    0.07
    zo
    0.07
    <Class
    0.07
    CX
    0.06
    ']));
    0.06
    072
    0.06
    Cash
    0.06
    Activations Density 0.003%

    No Known Activations