© 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. 78438
    Prev
    Next
    INDEX
    Explanations

    references to Mars and its associated characteristics or phenomena

    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
    ipo
    -0.07
    hana
    -0.06
     of
    -0.06
     tr
    -0.05
    nger
    -0.05
    avy
    -0.05
     train
    -0.05
    Uvs
    -0.05
    less
    -0.05
     seal
    -0.05
    POSITIVE LOGITS
    piel
    0.07
    ubyte
    0.07
    ův
    0.07
    Å¡Å¥
    0.07
    spiel
    0.07
    ienne
    0.07
    .LookAndFeel
    0.07
    alem
    0.07
    umpy
    0.07
    benh
    0.07
    Activations Density 0.006%

    No Known Activations