© 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. 84871
    Prev
    Next
    INDEX
    Explanations

    references to GitHub and related code repositories

    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
    anlı
    -0.07
    inand
    -0.06
    inning
    -0.06
    stood
    -0.06
    gz
    -0.06
    riz
    -0.06
    allon
    -0.06
    ieux
    -0.06
    ioned
    -0.06
    ails
    -0.06
    POSITIVE LOGITS
    ż
    0.07
     plant
    0.06
     Kraj
    0.06
     Coch
    0.06
    ernals
    0.06
    asmus
    0.06
    CursorPosition
    0.06
     Mei
    0.06
    ADX
    0.06
    plusplus
    0.06
    Activations Density 0.000%

    No Known Activations