© 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. 93190
    Prev
    Next
    INDEX
    Explanations

    forward slashes

    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
     Zus
    -0.06
     prov
    -0.06
     Rip
    -0.06
    chron
    -0.06
     Nem
    -0.06
    ect
    -0.06
     sm
    -0.06
     training
    -0.05
    gether
    -0.05
     Abs
    -0.05
    POSITIVE LOGITS
    ýt
    0.07
     kiến
    0.07
    ocu
    0.07
    voj
    0.07
    celed
    0.07
     Ñĩином
    0.07
    æµ·éģĵ
    0.07
     scalp
    0.07
    LocalizedString
    0.07
    _exports
    0.07
    Activations Density 0.000%

    No Known Activations