© 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. 56454
    Prev
    Next
    INDEX
    Explanations

    references to opposing sides in discussions or conflicts

    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
    ãĤ¥
    -0.07
    onda
    -0.07
    çek
    -0.07
    hong
    -0.07
    ede
    -0.07
    aura
    -0.07
    еÑģп
    -0.06
    essian
    -0.06
    erken
    -0.06
    lahoma
    -0.06
    POSITIVE LOGITS
     sides
    0.10
    /all
    0.08
     side
    0.08
     parties
    0.08
     camp
    0.07
    rin
    0.06
     camps
    0.06
    fram
    0.06
     alike
    0.06
     Doyle
    0.06
    Activations Density 0.009%

    No Known Activations