© 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. 86332
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific instrumentation and deployment

    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
     alleg
    -0.07
    /
    -0.06
     reg
    -0.06
     inf
    -0.06
     Sharing
    -0.06
    ,
    -0.06
     amb
    -0.05
    878
    -0.05
    .
    -0.05
     enjoyment
    -0.05
    POSITIVE LOGITS
     phóng
    0.09
    Brains
    0.08
    ãĥ¼ãĥĹ
    0.08
    .Fetch
    0.08
    -release
    0.07
    zÃŃ
    0.07
    ewire
    0.07
    ữu
    0.07
    RELEASE
    0.07
    iteral
    0.07
    Activations Density 0.000%

    No Known Activations