© 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. 129800
    Prev
    Next
    INDEX
    Explanations

    ib

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of myofibroblast cells (or their activation) within the text.

    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
     пош
    -0.07
     userManager
    -0.07
     pioneered
    -0.06
    ví
    -0.06
     männ
    -0.06
     noh
    -0.06
    enz
    -0.06
    Encode
    -0.06
     duplicates
    -0.06
     mc
    -0.06
    POSITIVE LOGITS
    Character
    0.07
    submit
    0.07
     ASP
    0.07
     Character
    0.07
    ραν
    0.06
     signup
    0.06
    вад
    0.06
     Fah
    0.06
    .advance
    0.06
     FITNESS
    0.06
    Activations Density 0.002%

    No Known Activations