© 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. 44272
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on local variable names in code (e.g. “fold,” “bank”), i.e. it detects identifier tokens where variables are declared or assigned.

    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
    _PROFILE
    -0.06
     sockaddr
    -0.06
    ierarchical
    -0.06
    basename
    -0.06
     Razor
    -0.06
    -process
    -0.06
     Hanson
    -0.06
     Spending
    -0.06
     postId
    -0.06
    {'
    -0.06
    POSITIVE LOGITS
    GIT
    0.07
     SEEK
    0.06
    式
    0.06
    吹
    0.06
     subpo
    0.06
    _DEFAULT
    0.06
    isky
    0.06
    zeit
    0.06
    =
    0.06
    (binding
    0.06
    Activations Density 0.011%

    No Known Activations