© 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. 84008
    Prev
    Next
    INDEX
    Explanations

    terms related to student activities and event management

    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
    Animated
    -0.06
    ewing
    -0.06
     Animated
    -0.06
    chi
    -0.06
     animated
    -0.06
    tra
    -0.06
    anto
    -0.05
    animated
    -0.05
     Walls
    -0.05
     drawing
    -0.05
    POSITIVE LOGITS
    mpar
    0.08
    mbH
    0.08
    oucher
    0.08
     Stem
    0.07
    kowski
    0.07
    jÃŃm
    0.07
    icher
    0.07
    ublish
    0.07
     prere
    0.07
    á»±
    0.07
    Activations Density 0.002%

    No Known Activations