© 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. 92125
    Prev
    Next
    INDEX
    Explanations

    references to processing and related action verbs

    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
    indow
    -0.08
     lẽ
    -0.07
    ê
    -0.07
    lesc
    -0.07
    TeX
    -0.07
    quam
    -0.06
    oloj
    -0.06
    isc
    -0.06
    itter
    -0.06
    icias
    -0.06
    POSITIVE LOGITS
    ional
    0.10
    sing
    0.09
    ual
    0.09
    urement
    0.09
    ors
    0.08
    /display
    0.08
    edImage
    0.08
    sed
    0.08
    uality
    0.08
    edly
    0.08
    Activations Density 0.045%

    No Known Activations