© 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. 17-LLAMASCOPE-RES-131K
    11. 82402
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to medical research

    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
     Leban
    -0.07
    AVE
    -0.06
    á»ĭ
    -0.06
    ithub
    -0.06
    laughter
    -0.06
     hormones
    -0.06
    pitch
    -0.06
    ListOf
    -0.06
    [".
    -0.05
     flo
    -0.05
    POSITIVE LOGITS
     TMPro
    0.07
    PixelFormat
    0.07
    گاÙĨ
    0.07
     jadx
    0.07
     Bernardino
    0.06
    ormsg
    0.06
    ó
    0.06
    ĨĴ
    0.06
    _tid
    0.06
    ufs
    0.06
    Activations Density 0.001%

    No Known Activations