© 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. 81480
    Prev
    Next
    INDEX
    Explanations

    information related to events and schedules

    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
    aight
    -0.06
     *)((
    -0.06
     tonight
    -0.06
     Tonight
    -0.06
     Sundays
    -0.06
    ober
    -0.06
     اÙĦÙĬ
    -0.06
    .backend
    -0.06
    asz
    -0.06
    tf
    -0.06
    POSITIVE LOGITS
    åįĪ
    0.10
     lunch
    0.09
     afternoon
    0.09
     lunches
    0.08
     Lunch
    0.08
     morning
    0.08
    illac
    0.08
     breakout
    0.08
     day
    0.07
     breakfast
    0.07
    Activations Density 0.035%

    No Known Activations