© 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. 107837
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to systems, methods, and their associated constraints or uncertainties

    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
    ifter
    -0.07
    yr
    -0.07
    Į¨
    -0.07
    .qml
    -0.07
     Hers
    -0.06
    Aspect
    -0.06
    apter
    -0.06
    ?type
    -0.06
    omm
    -0.06
    cela
    -0.06
    POSITIVE LOGITS
    itez
    0.06
     Sad
    0.06
    inery
    0.06
    364
    0.06
     Stan
    0.06
    panse
    0.05
    atik
    0.05
     Ñĥг
    0.05
    yster
    0.05
    Sad
    0.05
    Activations Density 0.154%

    No Known Activations