© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 57801
    Prev
    Next
    INDEX
    Explanations

    instances of discourse markers and conversational transitions

    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
    ulen
    -0.07
    ÌĨ
    -0.07
     èĹ
    -0.07
    ivo
    -0.06
    dea
    -0.06
    udent
    -0.06
    StackNavigator
    -0.06
    oun
    -0.06
    .RightToLeft
    -0.06
    ÌĪ
    -0.06
    POSITIVE LOGITS
     etc
    0.13
    etc
    0.12
    //{{
    0.07
    things
    0.06
     pont
    0.06
    avir
    0.06
    thing
    0.06
    OLEAN
    0.06
    agh
    0.06
    ilog
    0.06
    Activations Density 0.056%

    No Known Activations