© 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. 62534
    Prev
    Next
    INDEX
    Explanations

    themes related to community engagement and support

    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
    .userInteractionEnabled
    -0.07
    oleÄį
    -0.07
    iske
    -0.06
     dur
    -0.06
    eld
    -0.06
    .fml
    -0.06
    ë¶
    -0.06
    澤
    -0.06
    loi
    -0.06
    ucc
    -0.06
    POSITIVE LOGITS
     non
    0.19
     Non
    0.16
    Non
    0.15
     NON
    0.15
    non
    0.15
     without
    0.15
    éĿŀ
    0.15
    _non
    0.15
    -non
    0.14
    (non
    0.14
    Activations Density 0.003%

    No Known Activations