© 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. 93806
    Prev
    Next
    INDEX
    Explanations

    phrases that convey a sense of novelty or new experiences

    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
    lok
    -0.06
    lops
    -0.06
    panion
    -0.06
    ework
    -0.06
    _PKG
    -0.06
    .www
    -0.06
     Hamilton
    -0.06
    âm
    -0.06
    deo
    -0.06
    046
    -0.06
    POSITIVE LOGITS
     appreciation
    0.08
    ively
    0.08
     Apprec
    0.08
    oser
    0.07
     possibilities
    0.07
     možnosti
    0.07
     understanding
    0.07
     perspective
    0.07
    stå
    0.07
     Previously
    0.06
    Activations Density 0.019%

    No Known Activations