© 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. 9-LLAMASCOPE-RES-131K
    11. 98595
    Prev
    Next
    INDEX
    Explanations

    references to mathematical or coding operations involving violations and constraints

    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
    774
    -0.06
     Phạm
    -0.06
     Hayden
    -0.06
    618
    -0.06
    imeo
    -0.06
    068
    -0.06
    RID
    -0.06
    064
    -0.06
    ENO
    -0.06
    dG
    -0.06
    POSITIVE LOGITS
    Äįer
    0.07
    UTERS
    0.07
     Ekon
    0.07
     ZemÄĽ
    0.07
    achuset
    0.07
    Sab
    0.07
    Ø«ÛĮر
    0.07
     rekl
    0.07
    lesia
    0.07
    hos
    0.07
    Activations Density 0.043%

    No Known Activations