© 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. 17-LLAMASCOPE-RES-131K
    11. 79070
    Prev
    Next
    INDEX
    Explanations

    terms related to competition and winning

    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
    odos
    -0.09
    ÑĪев
    -0.08
     Moines
    -0.08
     defaultMessage
    -0.07
    Äįást
    -0.07
    odia
    -0.07
    932
    -0.07
    INGTON
    -0.07
    izo
    -0.07
    ruba
    -0.07
    POSITIVE LOGITS
     automatically
    0.08
     will
    0.07
     Automatically
    0.07
     Lazar
    0.07
     automatic
    0.06
    ones
    0.06
     then
    0.06
     pow
    0.06
     Pow
    0.06
     plus
    0.06
    Activations Density 0.007%

    No Known Activations