© 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. 79804
    Prev
    Next
    INDEX
    Explanations

    sequences of movement or progression in a narrative context

    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
    877
    -0.06
    979
    -0.06
     slic
    -0.06
    arel
    -0.06
    888
    -0.06
     interchange
    -0.05
     upstream
    -0.05
     ArgumentOutOfRangeException
    -0.05
    317
    -0.05
    oun
    -0.05
    POSITIVE LOGITS
    ữu
    0.07
    à¹Īà¸Ńย
    0.07
    ики
    0.07
    iglia
    0.07
    _radi
    0.07
    igmoid
    0.07
    emailer
    0.07
    /Peak
    0.06
     Leone
    0.06
    oton
    0.06
    Activations Density 0.019%

    No Known Activations