© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 105332
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols related to graph theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edula
    -0.08
    IFORM
    -0.07
    imuth
    -0.07
    İ
    -0.07
    gio
    -0.07
    ulet
    -0.07
    ulent
    -0.07
    lom
    -0.07
    apter
    -0.07
    othy
    -0.07
    POSITIVE LOGITS
     Naz
    0.06
    ucid
    0.05
     Kimber
    0.05
    HTTPRequest
    0.05
     complement
    0.05
    206
    0.05
     Cle
    0.05
     Uncategorized
    0.05
    eton
    0.05
     Ned
    0.05
    Activations Density 0.167%

    No Known Activations