© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 126695
    Prev
    Next
    INDEX
    Explanations

    references to specific companies or brands

    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
    bjerg
    -0.07
    erial
    -0.06
     Hein
    -0.06
     Leone
    -0.06
     deco
    -0.06
     guild
    -0.06
    umbo
    -0.06
    ibu
    -0.06
    FirstChild
    -0.06
     Guild
    -0.06
    POSITIVE LOGITS
    ois
    0.08
    θμ
    0.07
    LL
    0.07
    vk
    0.06
    inder
    0.06
    querque
    0.06
     suce
    0.06
    _MO
    0.06
    dust
    0.06
    ResponseStatus
    0.06
    Activations Density 0.000%

    No Known Activations