© 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. 39437
    Prev
    Next
    INDEX
    Explanations

    references to neuroscience and related terminology

    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
     therefore
    -0.11
     Therefore
    -0.09
    Therefore
    -0.08
     daher
    -0.08
    pole
    -0.07
     Pose
    -0.07
    кап
    -0.07
    unicipio
    -0.07
     wiÄĻc
    -0.07
    urat
    -0.07
    POSITIVE LOGITS
    623
    0.07
    t
    0.07
    orphic
    0.07
    agma
    0.06
    iosity
    0.06
    eding
    0.06
    astle
    0.06
     Howe
    0.06
    zone
    0.06
     Mori
    0.06
    Activations Density 0.015%

    No Known Activations