© 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. 129826
    Prev
    Next
    INDEX
    Explanations

    instances of character interaction and dialogue in a narrative

    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
     '&#
    -0.07
    utin
    -0.07
    ictory
    -0.07
    csi
    -0.07
    CRY
    -0.07
    ritz
    -0.07
    å¿ľ
    -0.07
     Summon
    -0.07
     GetHashCode
    -0.07
    esty
    -0.06
    POSITIVE LOGITS
     turb
    0.07
    GLOBALS
    0.06
    igor
    0.06
     dem
    0.06
     talk
    0.06
     stayed
    0.06
     stays
    0.06
     ready
    0.06
    utility
    0.06
     bringing
    0.06
    Activations Density 0.053%

    No Known Activations