© 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 EvalsExportsAPI 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. 125692
    Prev
    Next
    INDEX
    Explanations

    the word "as" in various contexts

    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
    ovsky
    -0.06
    imbus
    -0.06
     only
    -0.06
    æĩ
    -0.06
    ivor
    -0.06
    mys
    -0.06
    isoft
    -0.05
    ates
    -0.05
    ista
    -0.05
    족
    -0.05
    POSITIVE LOGITS
    cert
    0.08
    paragus
    0.08
    close
    0.08
     close
    0.07
    ëĿ½
    0.07
    ething
    0.07
    oo
    0.07
    oty
    0.07
    vanced
    0.07
    yl
    0.07
    Activations Density 0.016%

    No Known Activations