© 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. 29041
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a starting point or entry into a topic or discussion

    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
    elper
    -0.07
    lov
    -0.07
    outs
    -0.07
     dikke
    -0.07
    aji
    -0.06
    ARGIN
    -0.06
     أش
    -0.06
    ido
    -0.06
    ÏĥÏĦε
    -0.06
     Hats
    -0.06
    POSITIVE LOGITS
    punkt
    0.08
     for
    0.08
     Jacobs
    0.08
    /end
    0.07
    /Base
    0.07
    /start
    0.06
    /base
    0.06
    ¡
    0.06
    forcement
    0.06
     vfs
    0.06
    Activations Density 0.010%

    No Known Activations