© 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. 15-LLAMASCOPE-RES-131K
    11. 87742
    Prev
    Next
    INDEX
    Explanations

    references to artistic and performance elements in various contexts

    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
    resh
    -0.06
    x
    -0.06
     recip
    -0.06
    i
    -0.06
     heads
    -0.05
    2
    -0.05
    201
    -0.05
    or
    -0.05
     Best
    -0.05
    inch
    -0.05
    POSITIVE LOGITS
    /cms
    0.10
    plib
    0.09
    .xz
    0.09
    eck
    0.08
    /Grid
    0.08
    ̣
    0.08
    íĥķ
    0.08
    frau
    0.08
    кÑĢаÑĹн
    0.08
    YRO
    0.08
    Activations Density 0.037%

    No Known Activations