© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9373
    Prev
    Next
    INDEX
    Explanations

    submission

    np_max-act · gemini-2.0-flash

    This neuron activates on grappling and submission terms (e.g., choke, armbar, submission) in MMA fight descriptions.

    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
     Aber
    -0.07
    GameData
    -0.07
     Ost
    -0.06
    Australia
    -0.06
    ทำให
    -0.06
     kế
    -0.06
    販売
    -0.06
     Sun
    -0.06
     Helps
    -0.06
     станд
    -0.06
    POSITIVE LOGITS
     underwear
    0.07
    icrosoft
    0.07
    (hw
    0.07
    (Model
    0.07
    ERİ
    0.06
    objc
    0.06
     profesional
    0.06
     FN
    0.06
     учас
    0.06
     içindeki
    0.06
    Activations Density 0.001%

    No Known Activations