© 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. 125726
    Prev
    Next
    INDEX
    Explanations

    references to locations and relationships between entities

    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
    others
    -0.08
     others
    -0.08
     ÑĤоÑīо
    -0.07
    imdi
    -0.07
    aket
    -0.07
    chandle
    -0.07
    /REC
    -0.07
    ฯ
    -0.07
    etc
    -0.07
    aka
    -0.07
    POSITIVE LOGITS
    çļĦæĺ¯
    0.09
     “
    0.07
    :↵↵
    0.06
     totiž
    0.06
     neither
    0.06
     rather
    0.06
     either
    0.06
    ãĢ
    0.06
    :
    0.06
     "
    0.06
    Activations Density 0.112%

    No Known Activations