© 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. 126167
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of movie genre labels (e.g. drama, acción, comedia, suspense, guerra, ciencia-ficción).

    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
     Luigi
    -0.07
    _threshold
    -0.06
    .Drop
    -0.06
    หย
    -0.06
    outil
    -0.06
     reviewing
    -0.05
    otch
    -0.05
    810
    -0.05
     зер
    -0.05
    bid
    -0.05
    POSITIVE LOGITS
     sanat
    0.07
    Gatt
    0.07
     sx
    0.07
     кого
    0.06
    I
    0.06
     Dimit
    0.06
     ive
    0.06
     Ive
    0.06
     ней
    0.06
    eric
    0.06
    Activations Density 0.028%

    No Known Activations