© 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. 92738
    Prev
    Next
    INDEX
    Explanations

    references to people, their relationships, and the context of narratives within the text

    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
    orex
    -0.08
    IBE
    -0.07
    angler
    -0.07
    ôt
    -0.07
    etch
    -0.07
    áli
    -0.07
    rió
    -0.07
    ersh
    -0.07
    \Migrations
    -0.07
    riday
    -0.07
    POSITIVE LOGITS
     being
    0.25
    being
    0.19
     Being
    0.17
    Being
    0.15
     having
    0.15
     sendo
    0.14
     becoming
    0.13
    被
    0.13
    -being
    0.11
     siendo
    0.11
    Activations Density 0.101%

    No Known Activations