© 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. 92466
    Prev
    Next
    INDEX
    Explanations

    audio

    np_max-act · gemini-2.0-flash

    This neuron fires on references to specific branded audio/video gear or plugin models (i.e. product and model names).

    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
    TG
    -0.07
    RuleContext
    -0.07
    858
    -0.06
     intertwined
    -0.06
    ايش
    -0.06
    دید
    -0.06
    ursed
    -0.06
     dernier
    -0.06
    REL
    -0.06
    بان
    -0.06
    POSITIVE LOGITS
     Locations
    0.07
    .Color
    0.07
    σει
    0.07
    │
    0.06
     opt
    0.06
     mastering
    0.06
     карт
    0.06
     Reduce
    0.06
     inspire
    0.06
     capable
    0.06
    Activations Density 0.053%

    No Known Activations