© 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. 25703
    Prev
    Next
    INDEX
    Explanations

    horror movies

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of the horror/terror genre in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    movies that are considered suspenseful or thrilling.

    oai_token-act-pair · gpt-4o-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
    zá
    -0.07
    _Metadata
    -0.07
     mối
    -0.06
    стре
    -0.06
    _spec
    -0.06
    (clone
    -0.06
    Apache
    -0.06
    arakter
    -0.06
     popis
    -0.06
    interface
    -0.06
    POSITIVE LOGITS
     pathway
    0.07
    inations
    0.07
     Watkins
    0.06
     jasmine
    0.06
     agitation
    0.06
    άς
    0.06
     /:
    0.06
     Un
    0.06
     Dah
    0.06
    ีด
    0.06
    Activations Density 0.058%

    No Known Activations