© 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. 84085
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding political positions and their implications

    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
    üçük
    -0.07
    lobby
    -0.06
    ocate
    -0.06
    ITTE
    -0.06
    roupon
    -0.06
    íĺ¸
    -0.06
    ITT
    -0.06
     lou
    -0.06
    eniz
    -0.06
    aptcha
    -0.06
    POSITIVE LOGITS
     winning
    0.07
    _WIN
    0.07
     win
    0.07
     Advis
    0.06
     WIN
    0.06
    estone
    0.06
     Electoral
    0.06
     disadvantage
    0.06
    mdl
    0.06
    105
    0.06
    Activations Density 0.016%

    No Known Activations