© 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. 80196
    Prev
    Next
    INDEX
    Explanations

    expressions of mixed emotions or conflicting feelings

    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
    ama
    -0.06
    egend
    -0.06
    fed
    -0.06
    erd
    -0.06
    ouse
    -0.06
    ship
    -0.06
    ai
    -0.06
     throw
    -0.06
     Care
    -0.06
    ĸ
    -0.06
    POSITIVE LOGITS
    lest
    0.08
    rens
    0.08
    isters
    0.07
     McKay
    0.07
    ctica
    0.07
    /Page
    0.07
    WXYZ
    0.07
    buz
    0.07
    inkle
    0.07
    Ø´ÛĮ
    0.07
    Activations Density 0.027%

    No Known Activations