© 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. 15-LLAMASCOPE-RES-131K
    11. 103764
    Prev
    Next
    INDEX
    Explanations

    references to political positions and actions regarding war and impeachment

    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
    té
    -0.08
    ToBounds
    -0.07
    uli
    -0.06
     Ramirez
    -0.06
    ê¹
    -0.06
    360
    -0.06
    PostBack
    -0.06
    veau
    -0.06
    PostExecute
    -0.06
    indre
    -0.06
    POSITIVE LOGITS
    atel
    0.06
    arta
    0.06
     final
    0.06
     did
    0.06
    _td
    0.06
     last
    0.06
    ets
    0.06
    èIJ¥ä¸ļ
    0.06
     adverts
    0.06
     cos
    0.06
    Activations Density 0.007%

    No Known Activations