© 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. 58235
    Prev
    Next
    INDEX
    Explanations

    punctuation and basic sentence structure elements

    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
    READ
    -0.06
    çķª
    -0.06
    eti
    -0.06
    bjerg
    -0.06
    Mi
    -0.06
    _EPS
    -0.06
    UNCT
    -0.06
    èĬ
    -0.06
     reg
    -0.06
    _ATTACH
    -0.06
    POSITIVE LOGITS
    ůr
    0.07
    -transitional
    0.07
    orde
    0.06
    Äħd
    0.06
     bisc
    0.06
    gam
    0.06
    istrov
    0.06
    kee
    0.06
    ucz
    0.06
    erken
    0.06
    Activations Density 0.003%

    No Known Activations