© 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. 126508
    Prev
    Next
    INDEX
    Explanations

    references to television shows or series

    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
    á»ĵi
    -0.07
    indow
    -0.07
    ubit
    -0.06
    ampie
    -0.06
    ord
    -0.06
    ̣
    -0.06
    resse
    -0.06
    berger
    -0.06
    isy
    -0.06
     lục
    -0.06
    POSITIVE LOGITS
    tas
    0.06
     Dudley
    0.06
    tes
    0.06
     dikke
    0.06
    ijken
    0.06
     federally
    0.06
     Glo
    0.05
    credited
    0.05
    /web
    0.05
     Credits
    0.05
    Activations Density 0.000%

    No Known Activations