© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 103195
    Prev
    Next
    INDEX
    Explanations

    question phrases regarding travel and packing

    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
    eson
    -0.07
    -datepicker
    -0.07
    agrams
    -0.07
    eder
    -0.07
    oe
    -0.07
    itled
    -0.06
    OrCreate
    -0.06
    TestCategory
    -0.06
     ÑĢоб
    -0.06
    latlong
    -0.06
    POSITIVE LOGITS
    .Span
    0.06
    shima
    0.06
    ts
    0.06
     Succ
    0.06
     wom
    0.06
    lero
    0.06
    crets
    0.06
     sans
    0.06
    alink
    0.06
    âĿ
    0.05
    Activations Density 0.003%

    No Known Activations