© 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. 81960
    Prev
    Next
    INDEX
    Explanations

    URL patterns and formatting in the text

    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
    etine
    -0.07
    itian
    -0.07
    ANTE
    -0.07
     žen
    -0.06
    ematik
    -0.06
    UBY
    -0.06
    -twitter
    -0.06
    elf
    -0.06
     MatSnackBar
    -0.06
    oten
    -0.06
    POSITIVE LOGITS
     âĢİ
    0.06
     last
    0.06
     nexus
    0.05
     Ket
    0.05
     Superior
    0.05
     Separ
    0.05
    äll
    0.05
    .Of
    0.05
     pron
    0.05
    avel
    0.05
    Activations Density 0.007%

    No Known Activations