© 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. 17446
    Prev
    Next
    INDEX
    Explanations

    references to specific music recordings and their catalog numbers

    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
    edii
    -0.07
    ruise
    -0.07
    agnostic
    -0.06
    sequ
    -0.06
    åĭĴ
    -0.06
    rab
    -0.06
    vern
    -0.06
    abstract
    -0.06
    Ïĩαν
    -0.06
     Forward
    -0.06
    POSITIVE LOGITS
    @testable
    0.07
     LP
    0.06
    LP
    0.06
    ãĤ¹ãĥ¬
    0.06
     releases
    0.06
     Burnett
    0.06
    issing
    0.06
    pressed
    0.06
    κά
    0.06
    021
    0.06
    Activations Density 0.004%

    No Known Activations