© 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. 27255
    Prev
    Next
    INDEX
    Explanations

    terms associated with organized groups, roles, and events

    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
     zah
    -0.07
     all
    -0.06
     freedom
    -0.06
    ýt
    -0.06
     a
    -0.06
     "
    -0.06
     det
    -0.06
    ãn
    -0.06
    ãĢ
    -0.06
     real
    -0.06
    POSITIVE LOGITS
    /main
    0.08
    ovu
    0.07
    grily
    0.07
    dek
    0.07
    edia
    0.07
    ationally
    0.07
    olia
    0.07
    imate
    0.07
    hevik
    0.07
    ÙĬÙĦا
    0.07
    Activations Density 0.012%

    No Known Activations