© 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. 117760
    Prev
    Next
    INDEX
    Explanations

    the emphasis on various types and quantities of elements or entities

    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
     certain
    -0.07
    lan
    -0.06
    erk
    -0.06
    ãĥ©ãĥ¼
    -0.06
    ta
    -0.06
    g
    -0.06
    uel
    -0.06
     sure
    -0.06
    bo
    -0.06
     Certain
    -0.06
    POSITIVE LOGITS
    .twimg
    0.08
    ENCHMARK
    0.08
    errick
    0.08
    uco
    0.07
    quat
    0.07
    اصÙĦÙĩ
    0.07
    ãĢħ
    0.07
    alus
    0.07
    ива
    0.07
    иÑĤÑĥ
    0.07
    Activations Density 0.023%

    No Known Activations