© 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. 85796
    Prev
    Next
    INDEX
    Explanations

    philosophical and theological contrasts within discussions of existence and creation

    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
    enko
    -0.06
    ware
    -0.06
    phia
    -0.06
    rosso
    -0.06
     Clo
    -0.06
    ogo
    -0.06
    ordin
    -0.06
    usk
    -0.06
    iki
    -0.06
    oltip
    -0.06
    POSITIVE LOGITS
     contrast
    0.28
     contrasts
    0.23
     Contrast
    0.22
    contrast
    0.22
     opposed
    0.21
     versus
    0.20
     compared
    0.19
     opposite
    0.18
     vs
    0.17
     oppose
    0.15
    Activations Density 0.070%

    No Known Activations