© 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. 30812
    Prev
    Next
    INDEX
    Explanations

    mentions of file formats, specifically related to images and articles

    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
    erb
    -0.07
    anz
    -0.06
     taken
    -0.06
    ct
    -0.06
     Ts
    -0.06
     anecd
    -0.06
     tr
    -0.06
    aken
    -0.05
    lor
    -0.05
    ough
    -0.05
    POSITIVE LOGITS
    UNUSED
    0.08
    UILayout
    0.08
    íĥķ
    0.07
    Crop
    0.07
    湯
    0.07
    EIF
    0.07
    AndView
    0.07
    IENT
    0.07
    Ä±ÅŁÄ±k
    0.07
    007
    0.07
    Activations Density 0.000%

    No Known Activations