© 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 EvalsExportsAPI 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. 118796
    Prev
    Next
    INDEX
    Explanations

    conditional statements or clauses in programming syntax

    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
    otherwise
    -0.10
     otherwise
    -0.10
     OTHERWISE
    -0.09
     Otherwise
    -0.09
    Otherwise
    -0.08
    عÙħ
    -0.07
    vice
    -0.07
    baÅŁ
    -0.07
     else
    -0.07
    .Interop
    -0.07
    POSITIVE LOGITS
    outine
    0.07
    538
    0.06
    ator
    0.06
     Demir
    0.06
    in
    0.06
    675
    0.06
    enum
    0.06
    ESA
    0.05
    uese
    0.05
    697
    0.05
    Activations Density 0.006%

    No Known Activations