© 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. 27320
    Prev
    Next
    INDEX
    Explanations

    references to the NBA and its related elements

    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
    thinkable
    -0.07
     à¹Ĩ
    -0.07
    obel
    -0.07
    ãĥŃãĥ¼
    -0.07
    inue
    -0.06
     Pole
    -0.06
    ylim
    -0.06
    нив
    -0.06
    ifié
    -0.06
    apult
    -0.06
    POSITIVE LOGITS
    .gov
    0.09
    isti
    0.07
     Anth
    0.07
    gov
    0.07
    PA
    0.07
    -wide
    0.06
    .owl
    0.06
    -China
    0.06
    /pro
    0.06
    Ú¯ÛĮر
    0.06
    Activations Density 0.007%

    No Known Activations