© 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. 9-LLAMASCOPE-RES-131K
    11. 95336
    Prev
    Next
    INDEX
    Explanations

    code comments or documentation markup in text

    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
     Merr
    -0.06
     Nimbus
    -0.06
    kus
    -0.06
    vetica
    -0.06
    erness
    -0.06
    sold
    -0.06
    loaded
    -0.05
    cken
    -0.05
    anim
    -0.05
    _LAYER
    -0.05
    POSITIVE LOGITS
    veau
    0.07
    ye
    0.07
    ahlen
    0.07
    à¥Ģर
    0.06
    ATAB
    0.06
     Weston
    0.06
     Coal
    0.06
     sá»ijng
    0.06
    ifa
    0.06
    961
    0.06
    Activations Density 0.008%

    No Known Activations