© 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 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. 126677
    Prev
    Next
    INDEX
    Explanations

    words that relate to the concept of art and its various forms

    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
    Ä
    -0.06
    hey
    -0.06
    ardi
    -0.06
    ases
    -0.06
    ual
    -0.06
    xin
    -0.06
     Basket
    -0.06
     periods
    -0.06
    æĢ§
    -0.06
     пÑĢиÑħод
    -0.06
    POSITIVE LOGITS
    838
    0.08
    otch
    0.08
    ANCH
    0.08
    von
    0.08
    urement
    0.07
    wi
    0.07
    reno
    0.07
    endale
    0.07
    @Id
    0.07
    bero
    0.07
    Activations Density 0.009%

    No Known Activations