© 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. 105321
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to subsets and 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
    ghi
    -0.06
    ----------------------------------------------------------------------↵
    -0.06
    vise
    -0.06
    å¼ĺ
    -0.06
    <small
    -0.06
    ãĤ¦ãĥĪ
    -0.06
    conversion
    -0.06
    ãĤ¤ãĤ¹
    -0.06
    ceb
    -0.06
     Tup
    -0.06
    POSITIVE LOGITS
    avors
    0.07
    otas
    0.07
     Picker
    0.06
    asher
    0.06
    umper
    0.06
    ozy
    0.06
    unal
    0.06
    emet
    0.06
    edeki
    0.06
    annie
    0.06
    Activations Density 0.064%

    No Known Activations