© 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. 84815
    Prev
    Next
    INDEX
    Explanations

    technical terms and instructions related to troubleshooting or repairing equipment

    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
    our
    -0.09
    ipp
    -0.07
    ament
    -0.07
    anks
    -0.07
    ours
    -0.06
    ips
    -0.06
    ienie
    -0.06
    ä¸ĸç´Ģ
    -0.06
    is
    -0.06
    ôn
    -0.06
    POSITIVE LOGITS
    .grp
    0.07
    оба
    0.07
    ç
    0.07
     Bilg
    0.06
    .Reporting
    0.06
     æ®
    0.06
    -fw
    0.06
    URITY
    0.06
     exclus
    0.06
    (Parameter
    0.06
    Activations Density 0.009%

    No Known Activations