© 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. 92949
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to market composition and performance

    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
    zl
    -0.06
    iminal
    -0.06
     Milf
    -0.06
     par
    -0.06
     e
    -0.06
    obox
    -0.05
     Bbw
    -0.05
     benchmark
    -0.05
    rippling
    -0.05
    reserve
    -0.05
    POSITIVE LOGITS
     contribution
    0.09
    åįł
    0.08
     share
    0.08
    mix
    0.08
    share
    0.08
     Contribution
    0.07
    contrib
    0.07
    å½¹
    0.07
    Share
    0.07
    aldi
    0.07
    Activations Density 0.017%

    No Known Activations