© 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. 59176
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about causality and reasons behind behaviors or phenomena

    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
    igin
    -0.07
    ãĥ«ãĥī
    -0.07
    ombine
    -0.07
    itur
    -0.07
    ombat
    -0.07
     bì
    -0.07
    ARAM
    -0.07
    PullParser
    -0.07
    orsi
    -0.07
    illis
    -0.07
    POSITIVE LOGITS
     despite
    0.09
     seemingly
    0.09
    /how
    0.07
     so
    0.07
     Despite
    0.07
     certain
    0.06
    Despite
    0.06
     fascination
    0.06
     successful
    0.06
    ecal
    0.06
    Activations Density 0.020%

    No Known Activations