© 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. 17756
    Prev
    Next
    INDEX
    Explanations

    references to competition and selection processes

    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
    pered
    -0.07
    ekler
    -0.07
    zy
    -0.06
     Düz
    -0.06
    oller
    -0.06
    disposing
    -0.06
    ilate
    -0.06
    .constants
    -0.06
    pcm
    -0.06
    ught
    -0.06
    POSITIVE LOGITS
    Å¡ÃŃ
    0.08
    Resolve
    0.07
    ioni
    0.07
    ofs
    0.06
    resolve
    0.06
     quyết
    0.06
     simple
    0.06
    -simple
    0.06
    /Runtime
    0.06
     Simple
    0.06
    Activations Density 0.008%

    No Known Activations