© 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. 42319
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to systems or processes, likely in a scientific or engineering 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
    TRS
    -0.07
    IELDS
    -0.07
    å¡
    -0.07
    gne
    -0.06
    ecycle
    -0.06
    LAG
    -0.06
    .Formatter
    -0.06
    ilm
    -0.06
    .Selenium
    -0.06
    оÑĢе
    -0.06
    POSITIVE LOGITS
    ushi
    0.07
    argon
    0.07
    une
    0.06
     Lust
    0.06
    BoxLayout
    0.06
    SourceType
    0.06
    546
    0.06
    lein
    0.05
    osto
    0.05
    ker
    0.05
    Activations Density 0.000%

    No Known Activations