© 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. 18166
    Prev
    Next
    INDEX
    Explanations

    themes related to open dialogue and debate

    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
    jez
    -0.07
    ooter
    -0.07
    дина
    -0.07
    stad
    -0.07
    oplayer
    -0.07
    leme
    -0.06
    Narrated
    -0.06
    onom
    -0.06
    .jasper
    -0.06
    ivery
    -0.06
    POSITIVE LOGITS
     discussion
    0.18
     discussions
    0.16
     conversation
    0.16
    discussion
    0.14
     conversations
    0.14
     Discussion
    0.14
    conversation
    0.13
     debate
    0.13
    Discussion
    0.13
     discuss
    0.13
    Activations Density 0.128%

    No Known Activations