© 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. 77539
    Prev
    Next
    INDEX
    Explanations

    events, especially those related to deadlines and timelines

    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
    .addElement
    -0.08
    anta
    -0.08
    iyim
    -0.07
    ANTA
    -0.07
    amel
    -0.07
    iddy
    -0.07
    berger
    -0.06
     اÙĦرسÙħÙĬ
    -0.06
    iros
    -0.06
    addock
    -0.06
    POSITIVE LOGITS
     but
    0.08
     instead
    0.08
    instead
    0.08
     Nope
    0.08
     failed
    0.07
     Instead
    0.07
    but
    0.07
     failing
    0.07
     fails
    0.07
     originally
    0.07
    Activations Density 0.052%

    No Known Activations