© 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. 80084
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax or identifiers

    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
    onga
    -0.07
    iya
    -0.07
    idy
    -0.07
    enties
    -0.06
    indy
    -0.06
    zier
    -0.06
    umpt
    -0.06
    rvé
    -0.06
    stÃŃ
    -0.06
    sled
    -0.06
    POSITIVE LOGITS
    ģm
    0.07
    ã
    0.06
    -slot
    0.06
    eldon
    0.06
    Cascade
    0.06
     Berkshire
    0.06
    ipur
    0.06
    _cu
    0.05
    .xls
    0.05
    thora
    0.05
    Activations Density 0.001%

    No Known Activations