© 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. 7601
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash

    questions related to technical debugging in programming.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects the “/number/” segments in jsFiddle URLs, firing on the slashes and digits that make up the code‐and‐revision part of those links.

    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
    .Drawable
    -0.06
     وص
    -0.06
    EG
    -0.06
     Beg
    -0.06
    _footer
    -0.06
    TREE
    -0.06
    .Zip
    -0.06
    arrera
    -0.06
    CHEDULE
    -0.06
    Mt
    -0.06
    POSITIVE LOGITS
     Scalars
    0.07
    ляються
    0.06
     interior
    0.06
     때문에
    0.06
    oteric
    0.06
     Lös
    0.06
    richt
    0.06
    .channel
    0.06
     communion
    0.06
     Covent
    0.06
    Activations Density 0.001%

    No Known Activations