© 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
    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. 42521
    Prev
    Next
    INDEX
    Explanations

    define

    np_max-act · gemini-2.0-flash

    The neuron fires on C preprocessor directives—especially lines that define or undefine macros (e.g. “Define,” “#define,” “#undef,” or feature‐test macros like HAVE_…).

    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
    くだ
    -0.07
     보내
    -0.07
    사를
    -0.07
    Chi
    -0.06
     Kuala
    -0.06
    نویس
    -0.06
     ghế
    -0.06
    цами
    -0.06
    ullivan
    -0.06
    ,ch
    -0.06
    POSITIVE LOGITS
    /'
    0.07
    _include
    0.07
    (stack
    0.06
     development
    0.06
     Empty
    0.06
    始
    0.06
     tearDown
    0.06
     die
    0.06
     towels
    0.06
    cdn
    0.06
    Activations Density 0.009%

    No Known Activations