© 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. 87728
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and characteristics suggesting quality, complexity, and dimensionality

    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
    urrets
    -0.07
     pornos
    -0.07
    ssql
    -0.07
    æ¹
    -0.07
    iec
    -0.06
    esso
    -0.06
     Im
    -0.06
    elier
    -0.06
    oise
    -0.06
     Sour
    -0.06
    POSITIVE LOGITS
     Livingston
    0.07
    argar
    0.07
    æģ
    0.07
    pling
    0.07
    å½»
    0.07
    apore
    0.06
    å¡ļ
    0.06
     ÙĨاØŃ
    0.06
    roids
    0.06
    dni
    0.06
    Activations Density 0.029%

    No Known Activations