© 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. 41971
    Prev
    Next
    INDEX
    Explanations

    references to narratives and stories that evoke emotional or community connections

    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
    quist
    -0.07
    usto
    -0.07
     Sweep
    -0.06
     Vinci
    -0.06
    viso
    -0.06
     bek
    -0.06
    WRAPPER
    -0.06
     sweep
    -0.06
    .AnchorStyles
    -0.06
     NOTICE
    -0.06
    POSITIVE LOGITS
     tricks
    0.07
     ropes
    0.07
    imits
    0.07
    agar
    0.07
     Tricks
    0.07
     about
    0.07
    utos
    0.06
    ÑĢоÑĤ
    0.06
    uras
    0.06
     facts
    0.06
    Activations Density 0.085%

    No Known Activations