© 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. 89241
    Prev
    Next
    INDEX
    Explanations

    contrast

    np_max-act · gemini-2.0-flash

    The neuron detects technical descriptions of contrast—i.e. mentions of “contrast” (and related enhancement terms) in imaging or visualization contexts.

    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
    	short
    -0.07
    Interrupt
    -0.07
    wx
    -0.06
     listening
    -0.06
    Sending
    -0.06
     زاده
    -0.06
     Twenty
    -0.06
     Wa
    -0.06
    dda
    -0.06
    _allowed
    -0.06
    POSITIVE LOGITS
    ><?=$
    0.06
     Repo
    0.06
    霍
    0.06
    tual
    0.06
    _OPTIONS
    0.06
     reverse
    0.06
    DMIN
    0.06
     attractions
    0.06
     док
    0.06
     continental
    0.06
    Activations Density 0.010%

    No Known Activations