© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 38958
    Prev
    Next
    INDEX
    Explanations

    code functions

    np_max-act · gemini-2.0-flash

    This neuron activates on code identifiers that are action‐verbs (i.e., function or method names like allocate, locate, optimize, execute, authenticate, summarize, initialize, validate).

    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
    bs
    -0.08
    iations
    -0.08
    =N
    -0.07
    N
    -0.06
    7
    -0.06
     N
    -0.06
     Oak
    -0.06
     members
    -0.06
    _h
    -0.06
    b
    -0.06
    POSITIVE LOGITS
    .generate
    0.08
     unite
    0.08
    ATE
    0.08
    це
    0.08
    ize
    0.08
    げ
    0.08
    configure
    0.08
    mé
    0.08
    ANTE
    0.08
    isé
    0.08
    Activations Density 0.036%

    No Known Activations