© 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. 116796
    Prev
    Next
    INDEX
    Explanations

    references to guidance and mentorship relationships

    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
    ãİ
    -0.07
    ilian
    -0.06
     Smoke
    -0.06
    Porno
    -0.06
     associate
    -0.06
    Äįer
    -0.06
    Tpl
    -0.06
     tors
    -0.06
     Fare
    -0.06
    indow
    -0.06
    POSITIVE LOGITS
    代
    0.07
     Harr
    0.07
     Unauthorized
    0.07
    essler
    0.07
    ghost
    0.06
    ãĥIJãĤ¤
    0.06
    ymm
    0.06
    ava
    0.06
    ormsg
    0.06
    é»ĺ
    0.06
    Activations Density 0.037%

    No Known Activations