© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 57955
    Prev
    Next
    INDEX
    Explanations

    elements of physical descriptions and representations in visual art

    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
    315
    -0.07
    hod
    -0.06
     Kos
    -0.06
    itous
    -0.06
    248
    -0.06
     sidew
    -0.06
    ENCIL
    -0.06
    isten
    -0.06
    inkle
    -0.06
    verity
    -0.06
    POSITIVE LOGITS
    umont
    0.07
    _OVERRIDE
    0.06
     censor
    0.06
    Edition
    0.06
    ãĥ«ãĥī
    0.06
    ylko
    0.06
    ears
    0.06
    kaar
    0.06
    Ïĥκε
    0.06
    unya
    0.06
    Activations Density 0.019%

    No Known Activations