© 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. 2332
    Prev
    Next
    INDEX
    Explanations

    elements of dress design and style

    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
    e
    -0.07
    thon
    -0.06
     embedded
    -0.06
    _ENCODING
    -0.06
    bar
    -0.06
     regret
    -0.06
    398
    -0.06
    576
    -0.06
    peak
    -0.06
    397
    -0.05
    POSITIVE LOGITS
    ä¸Ī
    0.09
    ndl
    0.08
    poly
    0.07
    æľ«
    0.07
    oulos
    0.07
     Hra
    0.07
    TAIL
    0.07
    erno
    0.07
    ãĥ¼ãĥī
    0.07
    oucher
    0.07
    Activations Density 0.015%

    No Known Activations