© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 124867
    Prev
    Next
    INDEX
    Explanations

    _n

    np_max-act · gemini-2.0-flash

    This neuron activates on code-style identifiers—tokens like variable names, file names, or API fields that include underscores, hyphens, or similar punctuation.

    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
     dorm
    -0.06
     honeymoon
    -0.06
     bedding
    -0.06
    HSV
    -0.06
    mother
    -0.06
    迅
    -0.06
     perfor
    -0.06
     brushes
    -0.06
    amaño
    -0.06
    Emitter
    -0.06
    POSITIVE LOGITS
    лл
    0.07
    ++){↵↵
    0.07
    avel
    0.06
    :B
    0.06
    899
    0.06
     حل
    0.06
    كوم
    0.06
     IS
    0.06
     passage
    0.06
     IB
    0.06
    Activations Density 0.043%

    No Known Activations