© 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 EvalsExportsinterp-engineNEWAPI 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. 81636
    Prev
    Next
    INDEX
    Explanations

    technical specifications and compatibility details related to USB connections

    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
    971
    -0.08
    938
    -0.08
    ÎŃαÏĤ
    -0.08
     gente
    -0.08
    оÑĩнÑĭй
    -0.07
    _stuff
    -0.07
    eldorf
    -0.07
    æ§
    -0.07
     à¤īल
    -0.07
    άνι
    -0.07
    POSITIVE LOGITS
     few
    0.09
     two
    0.09
     themselves
    0.07
     facts
    0.07
     meisten
    0.07
     and
    0.07
     words
    0.07
     three
    0.07
     these
    0.07
     those
    0.06
    Activations Density 0.185%

    No Known Activations