© 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. 74937
    Prev
    Next
    INDEX
    Explanations

    instances or occurrences of actions and events, particularly those related to 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
    phere
    -0.07
    ackle
    -0.07
    ÄĽÅ¾
    -0.07
    chw
    -0.07
    _TAC
    -0.07
    iddy
    -0.07
    polator
    -0.07
     artık
    -0.07
    quip
    -0.06
    ÙĨÙĪÛĮس
    -0.06
    POSITIVE LOGITS
     several
    0.16
     occasionally
    0.16
     twice
    0.15
     sometimes
    0.15
     occasions
    0.13
     often
    0.12
     instances
    0.12
    sometimes
    0.12
     Twice
    0.12
     frequently
    0.12
    Activations Density 0.162%

    No Known Activations