© 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. 71723
    Prev
    Next
    INDEX
    Explanations

    phrases and words suggesting improvement or enhancement

    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
    üçük
    -0.09
    -0.07
    ittest
    -0.07
     tük
    -0.07
    stry
    -0.07
    ãģĤãģ£ãģŁ
    -0.07
    eyim
    -0.07
    uff
    -0.07
    ych
    -0.07
    éné
    -0.07
    POSITIVE LOGITS
    -than
    0.17
     than
    0.16
    than
    0.14
    _than
    0.13
    idge
    0.12
     вÑģего
    0.11
     Than
    0.11
    Than
    0.11
    -known
    0.10
     THAN
    0.10
    Activations Density 0.028%

    No Known Activations