© 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 EvalsExportsAPI 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. 106659
    Prev
    Next
    INDEX
    Explanations

    complex character relationships and emotional depth 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
     bust
    -0.07
     f
    -0.07
     greatly
    -0.06
     Robert
    -0.06
    ..↵
    -0.06
     exact
    -0.06
     oc
    -0.06
     in
    -0.05
     n
    -0.05
     org
    -0.05
    POSITIVE LOGITS
    .MixedReality
    0.09
    .sax
    0.09
    лагод
    0.09
    .ValidationError
    0.08
    ï¿¥
    0.08
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    0.08
     pornografia
    0.08
    ÅĻejmÄĽ
    0.08
    _LOGGER
    0.08
    åľ¨çº¿éĺħ读
    0.08
    Activations Density 0.051%

    No Known Activations