© 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. 85329
    Prev
    Next
    INDEX
    Explanations

    references to academic journals and publishers

    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
    ipeg
    -0.07
    ERICA
    -0.07
    hiro
    -0.06
    cci
    -0.06
     prime
    -0.06
     Nationals
    -0.06
    /archive
    -0.06
     addCriterion
    -0.05
    het
    -0.05
    lector
    -0.05
    POSITIVE LOGITS
     Press
    0.13
    Press
    0.12
     press
    0.11
     presses
    0.11
    press
    0.11
     PRESS
    0.10
     publisher
    0.10
     publishers
    0.10
     Else
    0.10
    _press
    0.10
    Activations Density 0.218%

    No Known Activations