© 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. 89566
    Prev
    Next
    INDEX
    Explanations

    Internet data/code/email

    np_max-act · gemini-2.0-flash

    This neuron weakly activates on code‐like or non-English tokens (e.g. punctuation in code and Cyrillic words) rather than ordinary English words.

    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
     ホ
    -0.07
    loc
    -0.07
    Intensity
    -0.06
     план
    -0.06
     corrupt
    -0.06
    .skin
    -0.06
    .getDrawable
    -0.06
     fairness
    -0.06
    76
    -0.06
     sharedPreferences
    -0.06
    POSITIVE LOGITS
     ',↵
    0.07
     Magnum
    0.07
    *(
    0.07
     Lik
    0.07
     recv
    0.07
    ')
    ↵
    0.06
     lf
    0.06
    .commit
    0.06
    .Home
    0.06
     электр
    0.06
    Activations Density 0.000%

    No Known Activations