© 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. 15-LLAMASCOPE-RES-131K
    11. 87206
    Prev
    Next
    INDEX
    Explanations

    terms related to sequential or causal relationships

    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
    inks
    -0.07
     Lid
    -0.07
    iske
    -0.07
    uck
    -0.06
    apa
    -0.06
    ucken
    -0.06
    kaç
    -0.06
    azine
    -0.06
    away
    -0.06
    Ñĩе
    -0.06
    POSITIVE LOGITS
    chaft
    0.08
    ively
    0.08
    (before
    0.08
    urette
    0.08
    /Foundation
    0.08
    /current
    0.08
    ployment
    0.07
    /pre
    0.07
    lude
    0.07
    å¥ı
    0.07
    Activations Density 0.010%

    No Known Activations