© 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. 74029
    Prev
    Next
    INDEX
    Explanations

    phrases indicating opportunities or invitations to engage in conversation or learn more about a topic

    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
    reeze
    -0.07
    ождениÑı
    -0.06
    akistan
    -0.06
     Suarez
    -0.06
     clar
    -0.06
    gota
    -0.06
     Král
    -0.06
    647
    -0.06
    å¿ľ
    -0.06
    ÑĭÑģ
    -0.06
    POSITIVE LOGITS
     discussion
    0.09
     discuss
    0.09
     discussing
    0.09
     conversation
    0.08
     talk
    0.07
    .cv
    0.07
     discusses
    0.07
     discussed
    0.07
    oner
    0.07
    conversation
    0.07
    Activations Density 0.005%

    No Known Activations