© 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. 62143
    Prev
    Next
    INDEX
    Explanations

    references to characters and their relationships in narratives

    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
    rance
    -0.07
    ulp
    -0.06
    ous
    -0.06
     عاÙħÙĦ
    -0.06
    ng
    -0.06
    1
    -0.06
    ame
    -0.06
    ilet
    -0.06
    instance
    -0.06
    swick
    -0.06
    POSITIVE LOGITS
     ilk
    0.12
     alike
    0.08
     cohorts
    0.08
     associates
    0.08
     helpers
    0.08
     accomp
    0.07
    loys
    0.07
    ysl
    0.07
     associated
    0.07
     allies
    0.07
    Activations Density 0.018%

    No Known Activations