© 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. 82044
    Prev
    Next
    INDEX
    Explanations

    information related to educational resources and training opportunities

    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
    IVEN
    -0.08
    æ´¥
    -0.06
    exo
    -0.06
    âĸ¡âĸ¡
    -0.06
    óng
    -0.06
    иÑī
    -0.06
     dumb
    -0.06
    cord
    -0.06
     ob
    -0.06
    меÑģÑĤ
    -0.06
    POSITIVE LOGITS
     learn
    0.10
     Learn
    0.08
     learnt
    0.08
    learn
    0.08
     learning
    0.08
     learns
    0.07
    lernen
    0.07
     knowledge
    0.07
     step
    0.07
     covers
    0.07
    Activations Density 0.018%

    No Known Activations