© 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. 56117
    Prev
    Next
    INDEX
    Explanations

    elements of a network request or HTTP protocol details

    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
     Burton
    -0.06
    leur
    -0.06
    olf
    -0.06
     William
    -0.06
     Bry
    -0.06
     Taylor
    -0.05
    cept
    -0.05
     bomb
    -0.05
     Bomb
    -0.05
     reference
    -0.05
    POSITIVE LOGITS
    InSection
    0.09
    ëįķ
    0.08
     QVariant
    0.08
    racat
    0.08
    doll
    0.07
    ãĥ³ãĥIJ
    0.07
    -transitional
    0.07
    _pdu
    0.07
    agma
    0.07
    (strict
    0.07
    Activations Density 0.001%

    No Known Activations