© 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. 61984
    Prev
    Next
    INDEX
    Explanations

    concepts related to evaluation and performance measurement

    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
    kus
    -0.07
    ATAL
    -0.07
    ÌĨ
    -0.07
    AGED
    -0.06
    alo
    -0.06
    ìļ±
    -0.06
    ATAR
    -0.06
     menn
    -0.06
    elor
    -0.06
    /proto
    -0.06
    POSITIVE LOGITS
     progress
    0.13
     effectiveness
    0.12
     Progress
    0.10
     performance
    0.10
    performance
    0.08
    progress
    0.08
    -progress
    0.08
    _progress
    0.08
     success
    0.08
    formance
    0.08
    Activations Density 0.028%

    No Known Activations