© 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. 91639
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on isolated single-character alphabetic tokens (e.g. standalone letters used as variable names, labels, or identifiers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to scientific terminology and methodologies related to dental health research.

    oai_token-act-pair · gpt-4o-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
    (big
    -0.07
    gages
    -0.06
    .warn
    -0.06
    (children
    -0.06
     hurdles
    -0.06
    _ping
    -0.06
    .Exists
    -0.06
    .info
    -0.06
     μας
    -0.06
    antino
    -0.06
    POSITIVE LOGITS
    ifold
    0.07
     сили
    0.07
    看看
    0.07
     controlled
    0.07
    民
    0.06
    -Series
    0.06
     tal
    0.06
     ссыл
    0.06
     해외
    0.06
    ,V
    0.06
    Activations Density 0.051%

    No Known Activations