© 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. 106631
    Prev
    Next
    INDEX
    Explanations

    mentions of Facebook and related accounts

    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
     bund
    -0.06
    ç«ł
    -0.06
     vir
    -0.06
    æı
    -0.06
    ipherals
    -0.06
    sonian
    -0.06
    _WRAP
    -0.06
    Та
    -0.06
    akis
    -0.06
    irement
    -0.06
    POSITIVE LOGITS
     Timeline
    0.07
     ØŃساب
    0.07
     Road
    0.07
     timeline
    0.07
    abus
    0.06
     æŃ
    0.06
    loquent
    0.06
    jez
    0.06
    ubar
    0.06
     DateTimeOffset
    0.06
    Activations Density 0.000%

    No Known Activations