© 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. 15-LLAMASCOPE-RES-131K
    11. 87688
    Prev
    Next
    INDEX
    Explanations

    terms related to various locations and their attributes

    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
     Slater
    -0.06
     Tod
    -0.06
     Merk
    -0.06
    omap
    -0.06
    elt
    -0.06
    iddi
    -0.06
    vil
    -0.06
    omain
    -0.06
    kee
    -0.06
    isol
    -0.06
    POSITIVE LOGITS
     where
    0.10
    ãģ§ãģ®
    0.09
    ãģ§
    0.08
     ãģ§
    0.08
     hvor
    0.08
    where
    0.07
     où
    0.07
    	where
    0.07
    à¹Ħว
    0.07
     där
    0.07
    Activations Density 0.025%

    No Known Activations