© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 104256
    Prev
    Next
    INDEX
    Explanations

    references to various online resources or documentation links

    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
    adnÃŃ
    -0.08
    Äı
    -0.08
     addCriterion
    -0.08
    ynet
    -0.08
    arti
    -0.07
    .scalablytyped
    -0.07
    éļĽ
    -0.07
    isty
    -0.07
    oration
    -0.07
     huy
    -0.07
    POSITIVE LOGITS
    ↵
    0.07
    areth
    0.06
     instrument
    0.06
     folk
    0.06
     tend
    0.05
     pedigree
    0.05
     sant
    0.05
    780
    0.05
     manual
    0.05
     nin
    0.05
    Activations Density 0.001%

    No Known Activations