© 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. 62543
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their 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
    ież
    -0.06
     Teknik
    -0.06
     Inquiry
    -0.06
    λÏİ
    -0.06
     enqu
    -0.06
    òi
    -0.06
    _MEDIUM
    -0.06
    ova
    -0.06
    ambio
    -0.06
    esi
    -0.06
    POSITIVE LOGITS
     @
    0.08
    aybe
    0.07
    789
    0.07
    057
    0.07
    CTX
    0.07
    oha
    0.07
     fed
    0.07
    QUOTE
    0.07
     perch
    0.06
    711
    0.06
    Activations Density 0.007%

    No Known Activations