© 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. 121109
    Prev
    Next
    INDEX
    Explanations

    eligibility criteria and requirements for academic programs or fellowships

    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
    ubre
    -0.06
    unky
    -0.06
    iales
    -0.06
    yer
    -0.06
    benh
    -0.06
    omed
    -0.06
    averse
    -0.06
    puty
    -0.06
     Exit
    -0.06
     bá»ı
    -0.06
    POSITIVE LOGITS
    #
    0.07
    ãĥ«ãĤ¯
    0.06
     Rack
    0.06
     Pell
    0.06
    ldr
    0.06
    richt
    0.06
    STALL
    0.06
    .Must
    0.06
    ìŀ¬
    0.06
     Fritz
    0.06
    Activations Density 0.012%

    No Known Activations