© 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. 125755
    Prev
    Next
    INDEX
    Explanations

    significant moments or events in narrative storytelling

    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
    باØŃ
    -0.08
    991
    -0.08
    cisi
    -0.07
    imiter
    -0.07
     architekt
    -0.07
    оÑĢÑĤÑĥ
    -0.07
    olds
    -0.07
    Ùħز
    -0.07
    áºŃy
    -0.06
     jedn
    -0.06
    POSITIVE LOGITS
     recent
    0.10
     events
    0.07
     episode
    0.07
     when
    0.07
     Episode
    0.07
    uja
    0.06
     acts
    0.06
    arga
    0.06
     subsequent
    0.06
     recently
    0.06
    Activations Density 0.057%

    No Known Activations