© 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. 104378
    Prev
    Next
    INDEX
    Explanations

    key terms and concepts associated with definitions and their implications

    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
     named
    -0.06
    Named
    -0.06
     Leap
    -0.06
     Classified
    -0.06
     called
    -0.06
    ron
    -0.06
    ppo
    -0.06
    1
    -0.06
    abh
    -0.06
     numbering
    -0.06
    POSITIVE LOGITS
    USED
    0.09
    -used
    0.08
     Undefined
    0.08
    ilogy
    0.08
     Perf
    0.08
     ÑĥпоÑĤÑĢеб
    0.08
     used
    0.08
     USED
    0.08
    used
    0.07
    Used
    0.07
    Activations Density 0.033%

    No Known Activations