© 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. 95824
    Prev
    Next
    INDEX
    Explanations

    elements related to coding syntax or structure

    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
     [âĢ¦]
    -0.07
     pres
    -0.07
    éĢ
    -0.07
     [âĢ¦]↵
    -0.06
     Mec
    -0.06
    illas
    -0.05
    864
    -0.05
    aller
    -0.05
     tart
    -0.05
    lix
    -0.05
    POSITIVE LOGITS
    inou
    0.08
     cdecl
    0.07
     certif
    0.07
    .codes
    0.07
    hydr
    0.07
    duino
    0.07
    avian
    0.07
    icÃŃ
    0.07
    nos
    0.06
    cheng
    0.06
    Activations Density 0.023%

    No Known Activations