© 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. 17809
    Prev
    Next
    INDEX
    Explanations

    terms related to performance metrics and modeling techniques in computational systems

    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
    ainment
    -0.06
    Publication
    -0.06
     Publication
    -0.06
    \$
    -0.06
    uis
    -0.06
     exerc
    -0.06
    gages
    -0.06
     listOf
    -0.06
    241
    -0.06
     erst
    -0.06
    POSITIVE LOGITS
    inka
    0.07
    iminal
    0.07
    amage
    0.06
    485
    0.06
     Gaines
    0.06
    eel
    0.06
     Penn
    0.06
    MASK
    0.06
    shm
    0.06
     vamp
    0.06
    Activations Density 0.059%

    No Known Activations