© 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. 15462
    Prev
    Next
    INDEX
    Explanations

    themes of race and social justice 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
    ëĸ
    -0.07
    InternalServerError
    -0.07
    ì°©
    -0.07
    asel
    -0.07
     nack
    -0.07
    abby
    -0.07
     migli
    -0.07
     lô
    -0.06
    icient
    -0.06
    594
    -0.06
    POSITIVE LOGITS
     lighter
    0.07
     serious
    0.07
     sometimes
    0.07
     Rena
    0.07
    éĶĭ
    0.06
    rais
    0.06
     undert
    0.06
     moments
    0.06
    andle
    0.06
    _IOCTL
    0.06
    Activations Density 0.059%

    No Known Activations