© 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. 93933
    Prev
    Next
    INDEX
    Explanations

    expressions related to communication and conversation dynamics

    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
    imus
    -0.08
    lei
    -0.07
     Livingston
    -0.07
     mat
    -0.06
    rum
    -0.06
     scr
    -0.06
    宿
    -0.06
    roid
    -0.06
    sock
    -0.06
    rium
    -0.06
    POSITIVE LOGITS
     conversation
    0.09
     Conversation
    0.09
    Conversation
    0.08
     topics
    0.08
    conversation
    0.07
     topic
    0.07
    Segue
    0.07
    .topic
    0.07
     steer
    0.07
    /topic
    0.07
    Activations Density 0.007%

    No Known Activations