Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106696
    Prev
    Next
    INDEX
    Explanations

    date and time references

    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
    .scalablytyped
    -0.08
    XI
    -0.07
    333
    -0.07
    acman
    -0.07
     spir
    -0.07
    empor
    -0.07
    andler
    -0.07
     slu
    -0.07
    ÑĤик
    -0.06
    udi
    -0.06
    POSITIVE LOGITS
    .intellij
    0.07
    mil
    0.07
    ditor
    0.06
     Mil
    0.06
    Mil
    0.06
    _valor
    0.06
    EA
    0.06
    aser
    0.06
    affle
    0.06
    antar
    0.06
    Activations Density 0.001%

    No Known Activations