© 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. 85603
    Prev
    Next
    INDEX
    Explanations

    references to location, specifically the word "in" used repeatedly across different contexts

    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
    unity
    -0.06
    å¥Ĺ
    -0.06
    åĭ
    -0.06
    nic
    -0.06
    elik
    -0.06
    olina
    -0.06
    æĨ
    -0.06
     com
    -0.06
    /stretch
    -0.06
    045
    -0.06
    POSITIVE LOGITS
     or
    0.07
     unlucky
    0.07
    weg
    0.06
     lucky
    0.06
     luck
    0.06
    ัà¸įà¸į
    0.06
     doubts
    0.06
     doubt
    0.06
    eken
    0.06
    932
    0.06
    Activations Density 0.011%

    No Known Activations