© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38311
    Prev
    Next
    INDEX
    Explanations

    /cgi

    np_max-act · gemini-2.0-flash

    This neuron detects URL download links (particularly “cgi-bin” path segments and associated URL components) in documentation.

    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
    ilerden
    -0.07
    	tc
    -0.07
     sincerity
    -0.06
     Thy
    -0.06
     birden
    -0.06
     intercepted
    -0.06
    wild
    -0.06
    fdc
    -0.06
     taxed
    -0.06
    ських
    -0.06
    POSITIVE LOGITS
    gger
    0.07
    odge
    0.06
    vel
    0.06
    chsel
    0.06
    父亲
    0.06
    แกรม
    0.06
     essays
    0.06
     edits
    0.06
    gili
    0.06
     شهری
    0.06
    Activations Density 0.000%

    No Known Activations