Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 90016
    Prev
    Next
    INDEX
    Explanations

    online text snippets

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of video content and related media formats (e.g., “video,” “Blu-ray”).

    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
     swinger
    -0.07
    ز
    -0.06
     Como
    -0.06
    Luke
    -0.06
     charakter
    -0.06
    _added
    -0.06
    亚洲
    -0.06
    zing
    -0.06
     hell
    -0.06
     histogram
    -0.06
    POSITIVE LOGITS
     限
    0.07
    "][
    0.06
     kuzey
    0.06
    OMP
    0.06
     axs
    0.06
    .toolbox
    0.06
    Lexer
    0.06
     isempty
    0.06
     мяг
    0.06
    (ierr
    0.06
    Activations Density 0.545%

    No Known Activations