© 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. 107750
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to mathematical and statistical concepts

    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
    etler
    -0.06
     jump
    -0.06
    <a
    -0.06
    TZ
    -0.06
    ramer
    -0.06
    shaw
    -0.05
    746
    -0.05
     nearly
    -0.05
    avery
    -0.05
    vt
    -0.05
    POSITIVE LOGITS
     minus
    0.11
     versus
    0.08
     Measure
    0.08
    æij©
    0.07
    ово
    0.07
    ewan
    0.07
     subtract
    0.07
     divided
    0.07
     (%)
    0.07
     плÑİ
    0.07
    Activations Density 0.196%

    No Known Activations