© 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. 17852
    Prev
    Next
    INDEX
    Explanations

    references to evidence and theories surrounding religious and historical contexts

    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
     grip
    -0.06
     riff
    -0.06
    åĩĨ
    -0.06
     conclus
    -0.06
     schem
    -0.06
    kus
    -0.06
     recomm
    -0.06
     steal
    -0.05
    IfNeeded
    -0.05
     traps
    -0.05
    POSITIVE LOGITS
     evidence
    0.11
     Evidence
    0.10
    Evidence
    0.09
    ropa
    0.08
    vidence
    0.07
     ÎĶε
    0.07
     addCriterion
    0.07
     evid
    0.07
    imony
    0.07
     indirect
    0.07
    Activations Density 0.016%

    No Known Activations