© 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. 127005
    Prev
    Next
    INDEX
    Explanations

    references to various sports and related activities

    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
    pull
    -0.07
    Pull
    -0.07
     pulling
    -0.07
     punches
    -0.07
     plug
    -0.07
     pulled
    -0.07
     Plug
    -0.07
    udit
    -0.07
     pull
    -0.06
    steen
    -0.06
    POSITIVE LOGITS
     ball
    0.12
     balls
    0.11
    -ball
    0.09
     drib
    0.09
    çIJĥ
    0.09
     Ball
    0.09
     playable
    0.09
     Balls
    0.08
     BALL
    0.08
     gameplay
    0.08
    Activations Density 0.047%

    No Known Activations