© 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. 110854
    Prev
    Next
    INDEX
    Explanations

    {"

    np_max-act · gemini-2.0-flash

    The neuron chiefly detects floating-point number tokens (decimal literals with multiple digits after the point).

    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
    File
    -0.08
     přen
    -0.08
    　　
    -0.07
    +Sans
    -0.07
    _UP
    -0.07
    =}
    -0.07
     pública
    -0.07
    .navigate
    -0.07
     browse
    -0.07
    สะ
    -0.07
    POSITIVE LOGITS
    ={'
    0.09
     {"
    0.08
     a
    0.08
     {'
    0.08
    Ev
    0.07
    {"
    0.07
     Kh
    0.07
     CJ
    0.07
     aj
    0.07
     @{$
    0.07
    Activations Density 0.014%

    No Known Activations