© 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. 79497
    Prev
    Next
    INDEX
    Explanations

    references to structural or organizational features

    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
     Sesso
    -0.07
    YPD
    -0.07
    ernels
    -0.06
    aniu
    -0.06
    hani
    -0.06
    mh
    -0.06
    .BorderFactory
    -0.06
    ebek
    -0.06
    ford
    -0.06
    loh
    -0.06
    POSITIVE LOGITS
     themselves
    0.29
     itself
    0.28
     himself
    0.27
     herself
    0.26
     ourselves
    0.23
     Himself
    0.21
     oneself
    0.21
     yourself
    0.21
     zich
    0.20
     siÄĻ
    0.20
    Activations Density 0.067%

    No Known Activations