© 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. 91988
    Prev
    Next
    INDEX
    Explanations

    Movie plots and tropes

    np_max-act · gemini-2.0-flash

    The neuron flags film‐review tropes—words naming standard movie elements or clichés (love story, action heroes, song-dance routines, training montages, etc.).

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

    themes of action and adventure in narrative contexts.

    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
     Terrace
    -0.07
    씀
    -0.07
     unlaw
    -0.07
    Stmt
    -0.06
    ستی
    -0.06
    应当
    -0.06
     بلند
    -0.06
    Json
    -0.06
     dictionary
    -0.06
    _AREA
    -0.06
    POSITIVE LOGITS
    _se
    0.07
     Drag
    0.07
    ifo
    0.07
     campaigned
    0.06
     nuances
    0.06
    .embedding
    0.06
    _votes
    0.06
    .GO
    0.06
     deem
    0.06
    (EC
    0.06
    Activations Density 0.067%

    No Known Activations