© 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. 80328
    Prev
    Next
    INDEX
    Explanations

    instructions and processes related to repetitive actions

    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
    asley
    -0.07
     cemetery
    -0.06
    entifier
    -0.06
    OutOfRange
    -0.05
    ohl
    -0.05
    uchs
    -0.05
    tras
    -0.05
     im
    -0.05
     novice
    -0.05
    ardu
    -0.05
    POSITIVE LOGITS
     until
    0.38
    until
    0.34
     Until
    0.31
    Until
    0.30
    _until
    0.27
     till
    0.26
     hasta
    0.25
     jusqu
    0.23
    .until
    0.22
     até
    0.22
    Activations Density 0.136%

    No Known Activations