© 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. 84337
    Prev
    Next
    INDEX
    Explanations

    mentions of software updates and user experiences

    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
    hausen
    -0.07
     Released
    -0.06
    gon
    -0.06
    /tcp
    -0.06
    ar
    -0.06
     yourselves
    -0.06
    bits
    -0.06
    arts
    -0.06
    pron
    -0.06
    Å¡ak
    -0.06
    POSITIVE LOGITS
     yesterday
    0.12
     recent
    0.10
     suddenly
    0.09
     Yesterday
    0.09
    Yesterday
    0.09
    recent
    0.09
     recently
    0.09
    æĺ¨
    0.08
    çªģçĦ¶
    0.08
    uddenly
    0.08
    Activations Density 0.011%

    No Known Activations