© 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. 75832
    Prev
    Next
    INDEX
    Explanations

    code structure and programming syntax elements

    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
     already
    -0.09
    already
    -0.09
     Already
    -0.08
     már
    -0.08
    Already
    -0.08
    _already
    -0.07
     już
    -0.07
     Ñĥже
    -0.07
    ¯¯¯¯
    -0.06
    zero
    -0.06
    POSITIVE LOGITS
     continues
    0.10
     continue
    0.10
     still
    0.10
     remains
    0.09
     continued
    0.09
     masih
    0.09
     Continued
    0.09
     remain
    0.09
     Still
    0.08
     remained
    0.08
    Activations Density 0.019%

    No Known Activations