© 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. 89141
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases that denote assertions or claims

    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
    \<^
    -0.08
    acus
    -0.07
    togroup
    -0.07
     Král
    -0.07
    ologne
    -0.06
    andas
    -0.06
    IENTATION
    -0.06
    mbH
    -0.06
    ̣
    -0.06
     Lag
    -0.06
    POSITIVE LOGITS
     point
    0.08
     reference
    0.08
     rounds
    0.07
     claims
    0.07
     sure
    0.07
     comparison
    0.06
     clear
    0.06
     points
    0.06
    HG
    0.06
    ëı
    0.06
    Activations Density 0.015%

    No Known Activations