© 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. 107611
    Prev
    Next
    INDEX
    Explanations

    references to painting tools and techniques

    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
    üph
    -0.08
    angered
    -0.08
    Ñħо
    -0.08
    isters
    -0.08
    emp
    -0.08
    isor
    -0.07
    isle
    -0.07
    ej
    -0.07
    itä
    -0.07
    hue
    -0.07
    POSITIVE LOGITS
    (es
    0.12
    stroke
    0.09
    y
    0.08
    ES
    0.07
    es
    0.07
    wick
    0.07
    ero
    0.07
    landa
    0.07
    iness
    0.07
    /es
    0.07
    Activations Density 0.006%

    No Known Activations