© 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. 41794
    Prev
    Next
    INDEX
    Explanations

    technical specifications and model numbers related to products

    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
    .libs
    -0.08
    MDB
    -0.08
    osten
    -0.07
    igli
    -0.07
    ilip
    -0.07
    untas
    -0.07
    IDGET
    -0.07
    fak
    -0.07
    riger
    -0.07
    inis
    -0.07
    POSITIVE LOGITS
     Sid
    0.06
     Lords
    0.06
     sub
    0.06
     tent
    0.06
    CG
    0.05
     Luk
    0.05
     extended
    0.05
     CG
    0.05
     model
    0.05
    âĢį
    0.05
    Activations Density 0.077%

    No Known Activations