© 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. 73081
    Prev
    Next
    INDEX
    Explanations

    references to the physical layout and orientation of properties

    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
    haar
    -0.06
    avana
    -0.06
    ertext
    -0.06
    erver
    -0.06
    lish
    -0.06
    mpar
    -0.06
    zan
    -0.06
    elize
    -0.06
     Tribe
    -0.06
    头
    -0.05
    POSITIVE LOGITS
    imler
    0.07
    ç·
    0.07
     двоÑĢ
    0.07
    eus
    0.07
     swe
    0.06
     Cinder
    0.06
     tiener
    0.06
    ụ
    0.06
    isu
    0.06
    iset
    0.06
    Activations Density 0.007%

    No Known Activations