© 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. 62653
    Prev
    Next
    INDEX
    Explanations

    references to particular events or actions happening in the present or future

    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
    ovna
    -0.08
    ypse
    -0.08
    heimer
    -0.08
    ¸ı
    -0.07
    hire
    -0.07
    avr
    -0.07
    /read
    -0.07
    ึà¸ĩ
    -0.07
    ceae
    -0.07
    usercontent
    -0.07
    POSITIVE LOGITS
     lately
    0.10
     currently
    0.10
     now
    0.08
    anova
    0.08
     presently
    0.08
    currently
    0.08
     Currently
    0.08
     ÑģейÑĩаÑģ
    0.08
     Äijang
    0.07
    now
    0.07
    Activations Density 0.372%

    No Known Activations