© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109224
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    queries related to programming issues and code explanations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on tokens that are uppercase identifiers (often with underscores), such as Windows message constants (e.g. EN_CHANGE, WM_COMMAND, WM_NOTIFY) or all-caps schema/table names.

    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
     đột
    -0.07
    ></
    -0.07
    awah
    -0.07
    IMPLIED
    -0.06
    prox
    -0.06
    latlong
    -0.06
    mek
    -0.06
    ADR
    -0.06
    IDX
    -0.06
    _ISR
    -0.06
    POSITIVE LOGITS
    !'↵
    0.07
     Conspiracy
    0.07
    >Add
    0.06
    慢
    0.06
     ende
    0.06
     large
    0.06
    ,"↵
    0.06
    ????
    0.06
    .Refresh
    0.06
     vicious
    0.06
    Activations Density 0.109%

    No Known Activations