© 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. 38668
    Prev
    Next
    INDEX
    Explanations

    connections to specific documents or written materials

    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
     Brun
    -0.06
     uncon
    -0.06
     prime
    -0.05
    enÃŃ
    -0.05
     McD
    -0.05
     imp
    -0.05
     dual
    -0.05
     par
    -0.05
     t
    -0.05
    amp
    -0.05
    POSITIVE LOGITS
     document
    0.11
     documento
    0.10
    version
    0.09
    document
    0.09
     version
    0.09
     докÑĥменÑĤа
    0.08
    ahu
    0.08
    uhe
    0.08
    ocument
    0.08
    aoke
    0.08
    Activations Density 0.019%

    No Known Activations