© 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. 94992
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experience and creative endeavor

    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
     sẵn
    -0.07
    aminer
    -0.07
    blr
    -0.07
    ivot
    -0.07
    assy
    -0.07
    лÑıн
    -0.07
    दर
    -0.06
    oba
    -0.06
    cour
    -0.06
    PTR
    -0.06
    POSITIVE LOGITS
    ä¹ħ
    0.07
     freely
    0.07
     without
    0.07
    oret
    0.07
     potentially
    0.07
     truly
    0.07
     unlike
    0.07
    Really
    0.07
    rella
    0.06
    ono
    0.06
    Activations Density 0.087%

    No Known Activations