© 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. 58671
    Prev
    Next
    INDEX
    Explanations

    annotations related to code documentation and 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
    esz
    -0.08
    è¨Ģãģ£ãģŁ
    -0.07
    habi
    -0.07
    ÙħÙĤ
    -0.07
    geber
    -0.07
     scé
    -0.07
    Äįku
    -0.07
    nze
    -0.07
    TouchUpInside
    -0.07
    aptop
    -0.07
    POSITIVE LOGITS
     pure
    0.06
     rend
    0.06
     Gow
    0.06
    ILD
    0.06
    acs
    0.06
     gar
    0.06
     Manning
    0.05
     Bowen
    0.05
     sl
    0.05
     Kai
    0.05
    Activations Density 0.002%

    No Known Activations