© 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 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. 17-LLAMASCOPE-RES-131K
    11. 93861
    Prev
    Next
    INDEX
    Explanations

    terms related to vocabulary and language

    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
    imes
    -0.08
    gis
    -0.07
    (er
    -0.07
    843
    -0.07
    cher
    -0.07
    infeld
    -0.07
    erness
    -0.07
    chez
    -0.07
    Åĵ
    -0.07
    chner
    -0.07
    POSITIVE LOGITS
    ulaire
    0.09
    ulario
    0.08
    mith
    0.08
    न
    0.07
    ular
    0.07
    ãĤ·ãĤ¢
    0.07
    nge
    0.06
    oup
    0.06
    ITEM
    0.06
     Äijen
    0.06
    Activations Density 0.003%

    No Known Activations