© 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. 9-LLAMASCOPE-RES-131K
    11. 97508
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "home."

    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
    naire
    -0.11
    naires
    -0.09
    phan
    -0.08
    ries
    -0.08
    ÙĨ
    -0.08
    ments
    -0.08
    mentation
    -0.07
    leanup
    -0.07
    tempts
    -0.07
    ymology
    -0.07
    POSITIVE LOGITS
    grown
    0.09
    coming
    0.09
    à¯įà®
    0.07
    quist
    0.07
    court
    0.07
    ales
    0.07
    pe
    0.07
    stead
    0.07
    758
    0.07
    iday
    0.07
    Activations Density 0.077%

    No Known Activations