© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 61376
    Prev
    Next
    INDEX
    Explanations

    expressions of encouragement and participation in discussions

    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
    VE
    -0.06
    olie
    -0.05
     Ipsum
    -0.05
     generations
    -0.05
     WaitFor
    -0.05
     MotionEvent
    -0.05
    readcr
    -0.05
    ={"/
    -0.05
    appa
    -0.05
    amma
    -0.05
    POSITIVE LOGITS
     participation
    0.09
     Participation
    0.08
     participating
    0.08
    clc
    0.07
     participates
    0.07
     participants
    0.07
     ì°¸ìŬ
    0.07
     participate
    0.07
     participant
    0.07
    åıĤåĬł
    0.07
    Activations Density 0.005%

    No Known Activations