© 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. 97308
    Prev
    Next
    INDEX
    Explanations

    the word "some" in various 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
    ddit
    -0.07
    omanip
    -0.07
    baum
    -0.07
    oÄį
    -0.06
    ocache
    -0.06
    pNext
    -0.06
    nis
    -0.06
    endcode
    -0.06
    raya
    -0.06
    lixir
    -0.06
    POSITIVE LOGITS
     of
    0.07
    roph
    0.07
     Blades
    0.07
     воÑĢ
    0.06
    Scoped
    0.06
    ikler
    0.06
    çīĮ
    0.06
     metic
    0.06
    shall
    0.06
     ways
    0.06
    Activations Density 0.012%

    No Known Activations