© 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 EvalsExportsAPI 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. 56031
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of optical and photonic systems

    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
     answer
    -0.06
     answering
    -0.06
    mah
    -0.06
     undertaking
    -0.05
    ospace
    -0.05
     instantaneous
    -0.05
     lives
    -0.05
     wherever
    -0.05
     interior
    -0.05
     Von
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.08
    emean
    0.07
     пÑĢиклад
    0.07
    ÑĪÑĮ
    0.07
     вд
    0.07
     stimuli
    0.07
     KromÄĽ
    0.07
     stimulus
    0.07
    WithDuration
    0.07
    _DURATION
    0.07
    Activations Density 0.090%

    No Known Activations