© 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. 62719
    Prev
    Next
    INDEX
    Explanations

    concepts related to planning or participation in creative projects

    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
    rement
    -0.07
     almost
    -0.06
    esson
    -0.06
    arf
    -0.06
    нг
    -0.06
    lesai
    -0.06
     nearly
    -0.06
     frequently
    -0.06
     failed
    -0.06
    pline
    -0.06
    POSITIVE LOGITS
    something
    0.08
     something
    0.08
    mmo
    0.07
    omething
    0.07
    could
    0.07
    ymax
    0.07
    Could
    0.07
     somehow
    0.07
     instead
    0.07
    would
    0.07
    Activations Density 0.028%

    No Known Activations