© 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. 92770
    Prev
    Next
    INDEX
    Explanations

    HTML tags or elements meant for web content

    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
     disc
    -0.07
     sequ
    -0.06
    _EXPORT
    -0.06
     repl
    -0.06
     Albums
    -0.06
    isz
    -0.06
    ियत
    -0.06
    -Se
    -0.06
    _putchar
    -0.06
    idlo
    -0.06
    POSITIVE LOGITS
    athy
    0.07
    achu
    0.06
    ~/
    0.06
    CDATA
    0.06
    iche
    0.06
    ACHI
    0.06
    зна
    0.06
     Slate
    0.06
    UNDLE
    0.06
    _html
    0.06
    Activations Density 0.001%

    No Known Activations