© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 15849
    Prev
    Next
    INDEX
    Explanations

    references to items or concepts that can be located or discovered

    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
    jak
    -0.06
     shown
    -0.06
    OLLOW
    -0.06
    abr
    -0.06
    uw
    -0.06
    uell
    -0.06
    جÙĩ
    -0.06
    ì
    -0.06
     Chow
    -0.06
    loth
    -0.06
    POSITIVE LOGITS
     anywhere
    0.08
     Vict
    0.08
    igmat
    0.07
    /use
    0.07
    ohl
    0.07
    owitz
    0.06
    onet
    0.06
    735
    0.06
    imetype
    0.06
    enci
    0.06
    Activations Density 0.015%

    No Known Activations