© 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. 15-LLAMASCOPE-RES-131K
    11. 87690
    Prev
    Next
    INDEX
    Explanations

    information about individuals and their achievements, particularly in the context of fame and identity

    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
    Calibri
    -0.08
    thane
    -0.08
    FLASH
    -0.08
    lesia
    -0.07
    æı
    -0.07
    agraph
    -0.07
    Ñĥже
    -0.07
    ç¸
    -0.07
    indow
    -0.07
    gte
    -0.07
    POSITIVE LOGITS
     Wing
    0.07
     wing
    0.06
    C
    0.06
     profile
    0.05
    I
    0.05
    1
    0.05
    My
    0.05
     south
    0.05
     height
    0.05
     right
    0.05
    Activations Density 0.007%

    No Known Activations