© 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. 31287
    Prev
    Next
    INDEX
    Explanations

    words related to suitability and appropriateness for 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
    no
    -0.07
    eyh
    -0.07
    omet
    -0.06
    ç²
    -0.06
    utz
    -0.06
    ucc
    -0.06
    вод
    -0.06
    olt
    -0.06
    nette
    -0.06
    ÑĢез
    -0.06
    POSITIVE LOGITS
    ably
    0.12
    /app
    0.09
    weise
    0.08
    -for
    0.08
     for
    0.07
    ë¡ľëĬĶ
    0.07
    ively
    0.07
    -sized
    0.07
    mach
    0.07
    .UnitTesting
    0.07
    Activations Density 0.007%

    No Known Activations