© 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. 41906
    Prev
    Next
    INDEX
    Explanations

    discussions about flawed and complex characters 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
    _cmos
    -0.08
    adr
    -0.08
    mouseleave
    -0.07
    .nlm
    -0.07
    GMEM
    -0.07
    ãĤ¾
    -0.07
    ););↵
    -0.07
    PropertyValue
    -0.07
    asurement
    -0.07
    jem
    -0.07
    POSITIVE LOGITS
     imperfect
    0.11
     imper
    0.09
     fall
    0.09
     human
    0.08
     Imper
    0.08
     sometimes
    0.08
     occasionally
    0.08
     flawed
    0.08
    warts
    0.07
     messy
    0.07
    Activations Density 0.044%

    No Known Activations