© 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. 107832
    Prev
    Next
    INDEX
    Explanations

    terms related to authority or governing bodies

    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
    uthor
    -0.07
    uesta
    -0.06
    iform
    -0.06
    apur
    -0.06
    PRESS
    -0.06
    ught
    -0.06
    ainer
    -0.06
    ibar
    -0.06
    ault
    -0.06
    EA
    -0.06
    POSITIVE LOGITS
     did
    0.08
     do
    0.08
     does
    0.07
     ones
    0.07
     à¤ķरत
    0.07
     would
    0.07
     theirs
    0.07
    ìķħ
    0.06
    Indented
    0.06
     váºŃy
    0.06
    Activations Density 0.016%

    No Known Activations