© 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. 13779
    Prev
    Next
    INDEX
    Explanations

    battles

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on words referring to warfare or combat (e.g. “battle,” “fought,” “between”).

    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
     fasting
    -0.06
    Opens
    -0.06
     roleName
    -0.06
    orte
    -0.06
    (Cs
    -0.06
    견
    -0.06
    _token
    -0.06
     redund
    -0.06
     Bethesda
    -0.06
    riding
    -0.06
    POSITIVE LOGITS
     pls
    0.07
     Such
    0.07
    呼ば
    0.07
    ा↵↵
    0.06
    _booking
    0.06
     erm
    0.06
    .game
    0.06
     slou
    0.06
    ,如
    0.06
    *);↵
    0.06
    Activations Density 0.040%

    No Known Activations