© 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. 7994
    Prev
    Next
    INDEX
    Explanations

    strict

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “strict” in code (e.g. strict mode directives, strict‐typed declarations, or flags/options named “strict”).

    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
    .Unsupported
    -0.07
    Names
    -0.07
     Opposition
    -0.07
     SearchResult
    -0.06
     liquidity
    -0.06
    되어
    -0.06
    基
    -0.06
     normals
    -0.06
    .Commands
    -0.06
    .paths
    -0.06
    POSITIVE LOGITS
     Money
    0.07
     alm
    0.06
    .isEmpty
    0.06
    ivar
    0.06
    getDate
    0.06
    ichern
    0.06
     pau
    0.06
     Visitor
    0.06
    Rights
    0.06
     Coat
    0.06
    Activations Density 0.004%

    No Known Activations