© 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. 15-LLAMASCOPE-RES-131K
    11. 86534
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be."

    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
    463
    -0.08
    _attached
    -0.07
    _mime
    -0.07
    697
    -0.07
    ãģ©
    -0.07
    kyt
    -0.07
    AGON
    -0.07
    ãĥĥãĤ«ãĥ¼
    -0.07
    айÑĤ
    -0.07
    toc
    -0.07
    POSITIVE LOGITS
    /w
    0.07
     sub
    0.06
    laden
    0.06
     Calling
    0.06
     Noon
    0.06
    lington
    0.05
    arrant
    0.05
    peria
    0.05
    ategory
    0.05
     yours
    0.05
    Activations Density 0.023%

    No Known Activations