© 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 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. 17-LLAMASCOPE-RES-131K
    11. 56175
    Prev
    Next
    INDEX
    Explanations

    questions and discussions about individual choices and their implications

    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
     Yüksek
    -0.07
    èĨ
    -0.07
    ｡
    -0.07
    .mu
    -0.07
    âĢ¦.↵↵
    -0.07
     ÑĤабли
    -0.07
    ãn
    -0.07
    ãĢ
    -0.07
    òi
    -0.07
    ाà¤
    -0.06
    POSITIVE LOGITS
     likewise
    0.12
    dit
    0.12
     similarly
    0.11
     dit
    0.10
     ebenfalls
    0.09
     Likewise
    0.08
     equally
    0.07
     Dit
    0.07
    Similarly
    0.07
     Similarly
    0.07
    Activations Density 0.048%

    No Known Activations