© 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. 81542
    Prev
    Next
    INDEX
    Explanations

    references to human existence and sentience

    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
    enheim
    -0.08
    stroy
    -0.08
    omba
    -0.08
    lock
    -0.07
    sters
    -0.07
    usercontent
    -0.07
    crest
    -0.07
     upd
    -0.07
    cess
    -0.07
    ácil
    -0.07
    POSITIVE LOGITS
    hood
    0.08
    /entity
    0.08
    /entities
    0.07
     who
    0.07
    eker
    0.07
    PIX
    0.07
     whom
    0.07
    /groups
    0.07
    ness
    0.07
    552
    0.06
    Activations Density 0.007%

    No Known Activations