© 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. 92767
    Prev
    Next
    INDEX
    Explanations

    mentions of different languages and ethnic groups

    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
    ixin
    -0.07
    iph
    -0.07
    ukkit
    -0.07
    shm
    -0.07
    .Apis
    -0.07
    odus
    -0.07
    iage
    -0.07
    eka
    -0.07
     Ow
    -0.07
    REFIX
    -0.07
    POSITIVE LOGITS
     languages
    0.06
    екаÑĢ
    0.06
    ören
    0.06
     Bilg
    0.06
     Farrell
    0.06
     rendering
    0.06
    ATS
    0.06
     Äijoán
    0.06
     vero
    0.06
     tongues
    0.06
    Activations Density 0.006%

    No Known Activations