© 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. 15-LLAMASCOPE-RES-131K
    11. 87349
    Prev
    Next
    INDEX
    Explanations

    phrases that involve comparisons or contrasts between concepts or cases

    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
    continued
    -0.09
     continued
    -0.08
    ylko
    -0.07
     Continued
    -0.07
    lie
    -0.07
    rie
    -0.07
    cont
    -0.07
    (cont
    -0.07
    _contin
    -0.07
    986
    -0.07
    POSITIVE LOGITS
     first
    0.10
     former
    0.09
     primero
    0.07
    第ä¸Ģ
    0.07
    first
    0.07
     eerste
    0.07
     primera
    0.07
    .first
    0.07
    former
    0.07
     첫
    0.06
    Activations Density 0.037%

    No Known Activations