© 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. 73917
    Prev
    Next
    INDEX
    Explanations

    references to specific names and terms in various 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
    iginal
    -0.08
    hdl
    -0.08
    _MT
    -0.08
    oldur
    -0.07
    allen
    -0.07
    eniable
    -0.07
    еÑģÑı
    -0.07
    uxe
    -0.07
    ominator
    -0.07
    iggs
    -0.07
    POSITIVE LOGITS
     n
    0.06
    æ¶
    0.06
     bid
    0.06
     som
    0.06
     Bid
    0.06
     dumb
    0.05
    ensem
    0.05
     Dillon
    0.05
    hev
    0.05
     intra
    0.05
    Activations Density 0.007%

    No Known Activations