© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29558
    Prev
    Next
    INDEX
    Explanations

    activities related to preparation and getting ready in the morning

    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
    ouv
    -0.08
     Lap
    -0.08
    lap
    -0.07
    places
    -0.07
    Ľå»º
    -0.07
     laps
    -0.07
    dsa
    -0.07
    ÅĻes
    -0.07
    ertino
    -0.07
    ansom
    -0.07
    POSITIVE LOGITS
     morning
    0.09
     breakfast
    0.07
     shower
    0.07
     mornings
    0.07
    adeon
    0.07
     Morning
    0.06
     Bened
    0.06
     dep
    0.06
     grooming
    0.06
     preparing
    0.06
    Activations Density 0.019%

    No Known Activations