© 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. 104671
    Prev
    Next
    INDEX
    Explanations

    punctuation and non-word characters

    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
    okit
    -0.07
    adelphia
    -0.06
    uppe
    -0.06
    okie
    -0.06
    ugar
    -0.06
    lesia
    -0.06
    woord
    -0.06
    incy
    -0.06
    lood
    -0.06
    lint
    -0.06
    POSITIVE LOGITS
    ERING
    0.08
    ANI
    0.07
    encil
    0.06
    dba
    0.06
    oves
    0.06
    ORIZ
    0.06
     mus
    0.06
     Lester
    0.06
    ovsky
    0.06
    xia
    0.06
    Activations Density 0.011%

    No Known Activations