© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 69106
    Prev
    Next
    INDEX
    Explanations

    numerical data and their relationships

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    meden
    -0.08
     TypeInfo
    -0.07
    (PHP
    -0.07
    ÑĤеÑĢи
    -0.07
    .oc
    -0.07
    interop
    -0.07
    .mdl
    -0.07
     IDX
    -0.07
    emsp
    -0.07
    gı
    -0.07
    POSITIVE LOGITS
    MOTE
    0.07
    aldi
    0.06
     Neue
    0.05
    é
    0.05
    íĿ
    0.05
    _MODULES
    0.05
     Cream
    0.05
    abi
    0.05
    act
    0.05
     Back
    0.05
    Activations Density 0.083%

    No Known Activations