© 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. 77250
    Prev
    Next
    INDEX
    Explanations

    contractions and their associated contexts in the text

    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
     _______,
    -0.09
     ”↵↵
    -0.08
    liš
    -0.08
     sice
    -0.08
    dux
    -0.07
    ltk
    -0.07
    ï¼Ĵï¼IJ
    -0.07
    orelease
    -0.07
    okit
    -0.07
     interv
    -0.07
    POSITIVE LOGITS
     also
    0.09
    also
    0.08
     auch
    0.07
     também
    0.07
    Also
    0.07
     también
    0.07
     Also
    0.07
     także
    0.07
     âĢ¦
    0.07
     quite
    0.07
    Activations Density 0.044%

    No Known Activations