© 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. 73857
    Prev
    Next
    INDEX
    Explanations

    numerical data related to time 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
    oS
    -0.07
    -CS
    -0.06
     åľ
    -0.06
     kms
    -0.06
    kili
    -0.06
     Dual
    -0.06
    iral
    -0.06
     cul
    -0.06
     directional
    -0.06
     Cons
    -0.06
    POSITIVE LOGITS
    ocale
    0.07
    <boost
    0.06
    zap
    0.06
    Ïİ
    0.06
    lez
    0.06
     ÑĪÑĤÑĥ
    0.06
    ाà¤ķ
    0.06
    rus
    0.06
    institution
    0.06
    DEL
    0.06
    Activations Density 0.024%

    No Known Activations