© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 58548
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to graph theory and equations

    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
    ooter
    -0.06
     Gilbert
    -0.06
    å§Ĩ
    -0.06
     Clyde
    -0.06
     Gibraltar
    -0.06
    iyel
    -0.06
    ousel
    -0.06
     Trem
    -0.06
    .scalablytyped
    -0.06
    ahoma
    -0.06
    POSITIVE LOGITS
     stakes
    0.07
    deg
    0.07
     ade
    0.07
    oss
    0.07
    gcd
    0.06
    mán
    0.06
     proj
    0.06
     dess
    0.06
    acher
    0.06
     addslashes
    0.06
    Activations Density 0.064%

    No Known Activations