© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91460
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric temperature values (e.g. the “18,” “20,” “°C” tokens) in weather descriptions.

    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
     От
    -0.07
     moistur
    -0.06
    لك
    -0.06
    ei
    -0.06
    Emp
    -0.06
    duck
    -0.06
    怒
    -0.06
     eps
    -0.06
    -pop
    -0.06
    POSITIVE LOGITS
    toJson
    0.07
    Unused
    0.06
    .Concat
    0.06
    (response
    0.06
    ประสบ
    0.06
     UNUSED
    0.06
     //----------------
    0.06
    -selected
    0.06
    .getAbsolutePath
    0.06
    (AL
    0.06
    Activations Density 0.007%

    No Known Activations