© 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. 68802
    Prev
    Next
    INDEX
    Explanations

    lyrics

    np_max-act · gemini-2.0-flash

    The neuron detects credit‐listing terms in show metadata—words naming creative roles or contributions (e.g. “music,” “lyrics,” “book,” “libretto,” “composed,” “choreographed,” etc.).

    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
     tit
    -0.07
     Sunset
    -0.06
    �
    -0.06
     Ur
    -0.06
     الأم
    -0.06
    ﺪ
    -0.06
     Rotation
    -0.06
    Gate
    -0.06
     poultry
    -0.06
    profile
    -0.06
    POSITIVE LOGITS
     removing
    0.07
    metics
    0.07
    Declare
    0.07
     skin
    0.06
     receiving
    0.06
     removes
    0.06
     Plain
    0.06
    ันท
    0.06
    iona
    0.06
     veri
    0.06
    Activations Density 0.003%

    No Known Activations