© 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. 61369
    Prev
    Next
    INDEX
    Explanations

    instances of collaboration or group participation

    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
    oppel
    -0.08
    amba
    -0.07
    á»įc
    -0.06
    oust
    -0.06
    isol
    -0.06
     Triumph
    -0.06
     Hire
    -0.06
    WidgetItem
    -0.06
    Occurred
    -0.06
    adele
    -0.06
    POSITIVE LOGITS
     besides
    0.09
     Besides
    0.07
     participating
    0.07
     involved
    0.07
    yms
    0.07
     apart
    0.07
       
    0.06
    Other
    0.06
     present
    0.06
     includ
    0.06
    Activations Density 0.019%

    No Known Activations