© 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. 69869
    Prev
    Next
    INDEX
    Explanations

    definitions or clarifications of abbreviations and acronyms

    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
    uh
    -0.06
    acias
    -0.06
     neur
    -0.06
    ÙĦØ©
    -0.06
    dep
    -0.06
    nost
    -0.06
    isl
    -0.06
    noon
    -0.06
    cg
    -0.05
    ucid
    -0.05
    POSITIVE LOGITS
    edBy
    0.07
    ombat
    0.07
    .fromFunction
    0.07
    ODO
    0.07
    _drvdata
    0.07
    .psi
    0.07
    egasus
    0.07
    ¶Į
    0.07
    ailer
    0.07
    à¸Ńะà¹Ħร
    0.07
    Activations Density 0.003%

    No Known Activations