© 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. 15054
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional connection and spiritual themes

    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
    orum
    -0.06
    alis
    -0.06
     Webseite
    -0.06
     complaints
    -0.06
    ican
    -0.05
    och
    -0.05
    _ACL
    -0.05
     er
    -0.05
    roud
    -0.05
    esor
    -0.05
    POSITIVE LOGITS
     offer
    0.20
     Offer
    0.18
     offered
    0.17
    offer
    0.17
    Offer
    0.16
     offers
    0.15
     oferta
    0.14
    Offers
    0.13
     invitation
    0.13
    _offer
    0.13
    Activations Density 0.063%

    No Known Activations