© 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. 128822
    Prev
    Next
    INDEX
    Explanations

    attention heads/layers

    np_max-act · gemini-2.0-flash

    This neuron lights up on special control/formatting tokens and model-architecture keywords (e.g. header delimiters like “<|start_header_id|>” or terms such as “Transformer” and “Decoder”).

    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
    連
    -0.07
     lễ
    -0.06
     Kenya
    -0.06
     Jacket
    -0.06
    kı
    -0.06
     click
    -0.06
    -most
    -0.06
    sockopt
    -0.06
    يب
    -0.06
     кле
    -0.06
    POSITIVE LOGITS
    Dirs
    0.07
     Genç
    0.07
     Lum
    0.07
     direction
    0.07
    hões
    0.07
    grand
    0.06
    _CANCEL
    0.06
     splitted
    0.06
     wallpapers
    0.06
    にお
    0.06
    Activations Density 0.003%

    No Known Activations