© 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. 72485
    Prev
    Next
    INDEX
    Explanations

    structural elements and organization in academic papers

    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
    byn
    -0.07
    Ìģ
    -0.07
    unting
    -0.06
     katkı
    -0.06
    iece
    -0.06
    Isl
    -0.06
    Åĵ
    -0.06
    zÃŃ
    -0.06
    ald
    -0.06
    leen
    -0.06
    POSITIVE LOGITS
     briefly
    0.09
     brief
    0.08
     section
    0.07
     discusses
    0.07
    brief
    0.07
     describes
    0.07
     breve
    0.07
     followed
    0.06
     lay
    0.06
     discussing
    0.06
    Activations Density 0.019%

    No Known Activations