© 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. 39447
    Prev
    Next
    INDEX
    Explanations

    references to items or concepts that can be categorized or quantified in specific contexts

    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
    usc
    -0.07
    jer
    -0.07
     targ
    -0.06
    129
    -0.06
    ipa
    -0.06
    izzle
    -0.06
    illing
    -0.06
    kus
    -0.06
    requires
    -0.06
    hard
    -0.06
    POSITIVE LOGITS
    imir
    0.07
    ulen
    0.06
    licken
    0.06
    æ¼
    0.06
    ICENSE
    0.06
    arel
    0.06
    ULE
    0.06
    iasi
    0.06
    #__
    0.06
    	when
    0.06
    Activations Density 0.018%

    No Known Activations