© 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. 5-LLAMASCOPE-RES-131K
    11. 126071
    Prev
    Next
    INDEX
    Explanations

    names of influential political leaders

    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
     Tale
    -0.07
    366
    -0.07
    erton
    -0.07
    خش
    -0.06
    ticks
    -0.06
    osg
    -0.06
     Westbrook
    -0.06
    ello
    -0.06
     Flatten
    -0.06
    ÃŃc
    -0.06
    POSITIVE LOGITS
    éĽ
    0.07
    age
    0.06
    alace
    0.06
    spotify
    0.06
     splash
    0.06
     Vera
    0.06
    yling
    0.06
    LEAN
    0.06
    ÑĥÑĢи
    0.06
    ostel
    0.06
    Activations Density 0.000%

    No Known Activations