© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89073
    Prev
    Next
    INDEX
    Explanations

    references to news media and publication names

    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
    ulla
    -0.06
    vard
    -0.06
    inda
    -0.06
    ollah
    -0.06
     Haven
    -0.06
    -0.06
    ibel
    -0.06
    stri
    -0.05
     Nob
    -0.05
    enstein
    -0.05
    POSITIVE LOGITS
     Mã
    0.08
    Telegram
    0.07
    WWW
    0.07
     ÑģмоÑĤ
    0.07
    Smoke
    0.07
    лÑĸÑĤ
    0.07
    /Framework
    0.07
    edm
    0.07
    \Input
    0.06
     $_[
    0.06
    Activations Density 0.003%

    No Known Activations