© 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. 9-LLAMASCOPE-RES-131K
    11. 97674
    Prev
    Next
    INDEX
    Explanations

    terms related to digital book formats and reading platforms

    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
     un
    -0.06
     involved
    -0.06
     grain
    -0.06
    seo
    -0.06
    519
    -0.05
    omor
    -0.05
     close
    -0.05
     ones
    -0.05
     p
    -0.05
    dir
    -0.05
    POSITIVE LOGITS
    ploy
    0.08
    /Table
    0.08
    GT
    0.07
     migrationBuilder
    0.07
     kaf
    0.07
    inka
    0.07
    ipple
    0.07
    ìĿ´ë¹Ħ
    0.07
    /table
    0.07
    ipse
    0.07
    Activations Density 0.002%

    No Known Activations