© 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. 43104
    Prev
    Next
    INDEX
    Explanations

    Code snippets and comments

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (decimal numbers) embedded in the text.

    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
    ่ต
    -0.06
    DV
    -0.06
    _until
    -0.06
    itori
    -0.06
     continually
    -0.06
    _texts
    -0.06
     spanking
    -0.06
     okamž
    -0.06
    MD
    -0.06
    ятно
    -0.06
    POSITIVE LOGITS
    Howard
    0.06
    協
    0.06
    *'
    0.06
     Syn
    0.06
    <i
    0.06
    .av
    0.06
     支
    0.06
    unciation
    0.06
    -frame
    0.06
     prakt
    0.06
    Activations Density 0.023%

    No Known Activations