© 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. 69780
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to data analysis and statistical fitting

    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
    yles
    -0.06
    isme
    -0.06
    ãĤ
    -0.06
    ÏĦιο
    -0.06
    wis
    -0.06
    eren
    -0.05
    Ĥ
    -0.05
     equiv
    -0.05
    587
    -0.05
    lash
    -0.05
    POSITIVE LOGITS
     linear
    0.11
     slope
    0.11
     curve
    0.11
    urve
    0.11
     Linear
    0.10
     Intercept
    0.10
     Curve
    0.10
     fitted
    0.10
     fitting
    0.10
     intercept
    0.10
    Activations Density 0.271%

    No Known Activations