© 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. 79818
    Prev
    Next
    INDEX
    Explanations

    topics related to problem-solving and conflict resolution

    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
    اط
    -0.09
    æŦ
    -0.07
    meli
    -0.07
    aka
    -0.07
    utm
    -0.07
    olarity
    -0.07
    umber
    -0.07
    unce
    -0.06
    etti
    -0.06
    illin
    -0.06
    POSITIVE LOGITS
    æ¯
    0.07
    GREE
    0.06
    inh
    0.06
    activex
    0.06
    ittest
    0.06
    icut
    0.06
    ãĥ
    0.06
     draw
    0.06
    ÙģاÙĤ
    0.06
     madrid
    0.06
    Activations Density 0.000%

    No Known Activations