© 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. 92209
    Prev
    Next
    INDEX
    Explanations

    terms related to engineering and technical specifications

    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
    леж
    -0.07
    ingo
    -0.07
    omor
    -0.07
     hereby
    -0.07
    uben
    -0.07
    ìĤ¬ë¬´
    -0.07
    cai
    -0.06
    Convention
    -0.06
    Å¡ek
    -0.06
    ini
    -0.06
    POSITIVE LOGITS
     also
    0.15
    also
    0.12
     occasionally
    0.12
    ä¹Łæľī
    0.12
     alternative
    0.11
     juga
    0.11
     ALSO
    0.10
     sometimes
    0.10
     Also
    0.10
    alternative
    0.10
    Activations Density 0.041%

    No Known Activations