© 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. 41360
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses that introduce contrasting ideas or opinions

    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
    eus
    -0.07
    ams
    -0.07
    è
    -0.07
    âh
    -0.07
    ppard
    -0.06
    ipzig
    -0.06
     although
    -0.06
    ojis
    -0.06
     various
    -0.06
    -sama
    -0.06
    POSITIVE LOGITS
     seriously
    0.07
    chy
    0.07
    cher
    0.07
    tes
    0.06
    irs
    0.06
    è´¥
    0.06
    ãĥ¥
    0.06
    jac
    0.06
    rie
    0.06
    ches
    0.06
    Activations Density 0.051%

    No Known Activations