© 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. 15-LLAMASCOPE-RES-131K
    11. 87654
    Prev
    Next
    INDEX
    Explanations

    concepts related to cost analysis and performance metrics

    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
     ÙģÙĪ
    -0.07
     vÃŃde
    -0.07
    ãĤ¤ãĥ¤
    -0.06
    nech
    -0.06
    ÙĪØ«
    -0.06
    ultipart
    -0.06
    Ú©Ø´
    -0.06
     addCriterion
    -0.06
    Backup
    -0.06
    Billing
    -0.06
    POSITIVE LOGITS
    elden
    0.08
    /Branch
    0.06
    EDI
    0.06
     score
    0.06
    oro
    0.06
    oga
    0.06
    ̣
    0.06
     Rt
    0.06
    elm
    0.06
    ÑĢÑĥн
    0.06
    Activations Density 0.043%

    No Known Activations