© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127020
    Prev
    Next
    INDEX
    Explanations

    fever

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of “fever” (especially in contexts of reduction, treatment, or numeric temperature values).

    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
    racat
    -0.07
     Guild
    -0.07
     knitting
    -0.06
    Obj
    -0.06
     pian
    -0.06
    ="-
    -0.06
     Mafia
    -0.06
     Intermediate
    -0.06
     gió
    -0.06
    _lm
    -0.06
    POSITIVE LOGITS
    -К
    0.07
     conex
    0.06
    declar
    0.06
     klar
    0.06
    aversable
    0.06
     god
    0.06
    WER
    0.06
    -buffer
    0.06
     government
    0.06
     Ancient
    0.06
    Activations Density 0.002%

    No Known Activations