© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6787
    Prev
    Next
    INDEX
    Explanations

    exploitation films

    np_max-act · gemini-2.0-flash

    This neuron fires on terms and phrases that refer to Italian genre cinema—especially Italian horror/Giallo film titles, styles, and characteristic gore descriptors.

    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
    (stock
    -0.07
     busca
    -0.07
    _fid
    -0.06
    (Y
    -0.06
    _CONV
    -0.06
     Conversion
    -0.06
    ابد
    -0.06
    zem
    -0.06
    668
    -0.06
     Writer
    -0.06
    POSITIVE LOGITS
     duż
    0.06
     Temper
    0.06
     scrimmage
    0.06
    xdc
    0.06
     frivol
    0.06
     noe
    0.06
    	↵↵↵
    0.06
    ุตบอล
    0.06
    ynamo
    0.06
    \Event
    0.06
    Activations Density 0.046%

    No Known Activations