© 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. 39236
    Prev
    Next
    INDEX
    Explanations

    references to designers and related professions

    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
    alu
    -0.07
    ador
    -0.07
    onders
    -0.07
    istas
    -0.07
    isted
    -0.07
    anter
    -0.07
    ISTA
    -0.07
    eldon
    -0.06
    aries
    -0.06
    ista
    -0.06
    POSITIVE LOGITS
     who
    0.08
    ically
    0.08
    ial
    0.08
    innen
    0.07
    panion
    0.07
    otle
    0.07
    ÃŃna
    0.07
    hip
    0.07
    ship
    0.07
    å³°
    0.07
    Activations Density 0.019%

    No Known Activations