© 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. 108457
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, events, or items 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
    eydi
    -0.08
     opat
    -0.08
    aille
    -0.08
    ted
    -0.07
    ÅĻet
    -0.07
     ...(
    -0.07
    наÑĢод
    -0.07
    Ả
    -0.07
    innacle
    -0.07
    tie
    -0.07
    POSITIVE LOGITS
    .scalablytyped
    0.06
     prelim
    0.06
     lect
    0.06
    osu
    0.06
     STDERR
    0.06
     AssemblyCopyright
    0.06
     divert
    0.06
     contr
    0.06
     RSS
    0.05
     consider
    0.05
    Activations Density 0.503%

    No Known Activations