© 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. 124179
    Prev
    Next
    INDEX
    Explanations

    instances of multimedia and demonstrations related to technology and innovation

    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
    çŃĸ
    -0.07
    ahy
    -0.07
     surveys
    -0.07
    å¤ĩ
    -0.07
    elow
    -0.06
    å°Ĭ
    -0.06
    /Internal
    -0.06
    itness
    -0.06
    _WARNINGS
    -0.06
    itzer
    -0.06
    POSITIVE LOGITS
     demonstration
    0.12
     demo
    0.10
    demo
    0.10
     demonstrations
    0.10
     demonstr
    0.10
     demonstrate
    0.10
     demonstrated
    0.09
    -demo
    0.09
     demonstrators
    0.09
     Demon
    0.08
    Activations Density 0.014%

    No Known Activations