© 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. 42111
    Prev
    Next
    INDEX
    Explanations

    references to competition and qualifications in a structured environment

    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
     Affero
    -0.07
     交
    -0.06
    wish
    -0.06
     Wish
    -0.06
    èĢĢ
    -0.06
    avian
    -0.06
    ái
    -0.06
    gg
    -0.06
     allegiance
    -0.06
     Inherits
    -0.06
    POSITIVE LOGITS
     fitness
    0.07
    emale
    0.07
     contrace
    0.06
    composite
    0.06
     exempt
    0.06
     training
    0.06
     Fitness
    0.06
    .ast
    0.06
     Lub
    0.06
    име
    0.06
    Activations Density 0.002%

    No Known Activations