© 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. 105361
    Prev
    Next
    INDEX
    Explanations

    words associated with names or titles in cultural or historical contexts

    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
    391
    -0.07
    graduate
    -0.07
    è
    -0.07
    amation
    -0.06
    aphore
    -0.06
    uments
    -0.06
    emark
    -0.06
    464
    -0.06
    а
    -0.06
    erdale
    -0.06
    POSITIVE LOGITS
    ëıĻìķĪ
    0.07
    EDIA
    0.07
    ELY
    0.07
     Howe
    0.06
    Uvs
    0.06
    ä¿Ĭ
    0.06
     Decompiled
    0.06
    .IsNullOr
    0.06
    ĵn
    0.06
     vit
    0.06
    Activations Density 0.040%

    No Known Activations