© 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. 89334
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting

    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
     hafta
    -0.08
    ityEngine
    -0.06
    ÄįnÄĽ
    -0.06
    ÅĻÃŃzenÃŃ
    -0.06
    ãĥĪãĥ«
    -0.06
    çªģ
    -0.06
     ?><?
    -0.06
    pert
    -0.06
     timespec
    -0.06
     dah
    -0.06
    POSITIVE LOGITS
    Advertisement
    0.07
     surve
    0.07
     tail
    0.06
    esinden
    0.06
     Hin
    0.06
     Advertisement
    0.06
    advertisement
    0.06
    iasm
    0.06
    _UNS
    0.06
    indre
    0.06
    Activations Density 0.000%

    No Known Activations