© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12716
    Prev
    Next
    INDEX
    Explanations

    charset

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of “charset” or character‐encoding parameters in source code.

    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
    άνα
    -0.08
     motorcycles
    -0.07
    Meg
    -0.07
    あげ
    -0.07
     panties
    -0.07
     सदस
    -0.07
    ,LOCATION
    -0.06
     Mädchen
    -0.06
    Installation
    -0.06
     Adj
    -0.06
    POSITIVE LOGITS
    Charset
    0.10
     Charset
    0.08
    charset
    0.08
    _CHARSET
    0.08
    _charset
    0.08
    set
    0.08
    .charset
    0.07
    Charsets
    0.07
    ---@
    0.07
    (Set
    0.07
    Activations Density 0.001%

    No Known Activations