© 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. 126253
    Prev
    Next
    INDEX
    Explanations

    clearly

    np_max-act · gemini-2.0-flash

    The neuron fires on emphatic commentary tokens—especially the word “clearly” (and its immediate assertion context) that marks a writer’s emphatic stance.

    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
     　 　 　 　 　 　 　
    -0.07
    たら
    -0.06
     prefs
    -0.06
    cs
    -0.06
     unspecified
    -0.06
    INSTANCE
    -0.06
    рол
    -0.06
    agnostic
    -0.06
     Package
    -0.06
     أغسطس
    -0.06
    POSITIVE LOGITS
     istiyor
    0.09
    lara
    0.07
    Clearly
    0.06
    unya
    0.06
    _radio
    0.06
     ALLOW
    0.06
     киш
    0.06
    =tmp
    0.06
     Clearly
    0.06
    ZONE
    0.06
    Activations Density 0.034%

    No Known Activations