© 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. 720
    Prev
    Next
    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash

    The neuron fires on the “B” token in assembly syscall descriptors (e.g. the “B” that precedes the numeric value in lines like “(S … B 2.763671875)”).

    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
    UFFIX
    -0.07
     перш
    -0.06
    .Mon
    -0.06
     является
    -0.06
    入れ
    -0.06
    胎
    -0.06
    _Ass
    -0.06
    .subtitle
    -0.06
    _brand
    -0.06
    زار
    -0.06
    POSITIVE LOGITS
    ";↵
    0.07
     televizyon
    0.06
    ?"↵
    0.06
    ");↵
    0.06
     gag
    0.06
    (loader
    0.06
    !"↵
    0.06
     وإ
    0.06
    .'↵↵
    0.06
    ".↵
    0.06
    Activations Density 0.001%

    No Known Activations