© 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. 108995
    Prev
    Next
    INDEX
    Explanations

    font

    np_max-act · gemini-2.0-flash

    The neuron fires on floating-point numeric literals (decimal style values) embedded in the markup.

    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
     stretch
    -0.07
    razier
    -0.07
     clears
    -0.07
    .expand
    -0.07
     побач
    -0.07
     Arg
    -0.07
     Kerr
    -0.07
     eased
    -0.06
    .Service
    -0.06
    Сп
    -0.06
    POSITIVE LOGITS
     Font
    0.08
    Font
    0.08
     Mon
    0.07
    ;font
    0.07
     font
    0.07
    font
    0.07
     pari
    0.07
    ์น
    0.07
    gun
    0.07
    _font
    0.07
    Activations Density 0.007%

    No Known Activations