© 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. 117235
    Prev
    Next
    INDEX
    Explanations

    expressions of self-awareness and personal struggle

    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
    oola
    -0.07
    awns
    -0.06
    allen
    -0.06
    gue
    -0.06
    endar
    -0.06
    actice
    -0.06
     âĢ¦↵
    -0.06
    itemid
    -0.06
    ctime
    -0.06
    ender
    -0.05
    POSITIVE LOGITS
    .Skin
    0.07
     meiden
    0.07
    _CNTL
    0.07
    ëĿ¼íĶ¼
    0.07
     ComVisible
    0.07
     frau
    0.07
     geil
    0.07
     подоб
    0.07
    wang
    0.07
    [System
    0.06
    Activations Density 0.058%

    No Known Activations