© 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. 5086
    Prev
    Next
    INDEX
    Explanations

    contrasting statements or qualifiers in arguments

    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
     zwar
    -0.08
     sogar
    -0.07
    imizer
    -0.07
     Sne
    -0.06
    plementation
    -0.06
    404
    -0.06
    anda
    -0.06
     dokonce
    -0.06
    ptal
    -0.06
    pus
    -0.06
    POSITIVE LOGITS
     also
    0.17
    also
    0.14
     ALSO
    0.13
     Also
    0.13
    Also
    0.13
     também
    0.12
     aussi
    0.11
    ä¹Łæľī
    0.11
     juga
    0.11
     cũng
    0.11
    Activations Density 0.031%

    No Known Activations