© 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 EvalsExportsinterp-engineNEWAPI 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. 62292
    Prev
    Next
    INDEX
    Explanations

    references to time and commitments

    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
     hashtags
    -0.07
    instagram
    -0.07
     hashtag
    -0.07
    iran
    -0.07
    éĽĨåIJĪ
    -0.06
     instagram
    -0.06
    (DBG
    -0.06
    irable
    -0.06
    754
    -0.06
    ilon
    -0.06
    POSITIVE LOGITS
    ream
    0.08
    inton
    0.07
    üc
    0.07
     zel
    0.06
    á»ijng
    0.06
    audio
    0.06
    PFN
    0.06
    util
    0.06
    ayın
    0.06
    eneric
    0.06
    Activations Density 0.000%

    No Known Activations