© 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. 40674
    Prev
    Next
    INDEX
    Explanations

    references to fact-checking and misinformation

    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
    ourse
    -0.07
     crust
    -0.06
    lier
    -0.06
    codegen
    -0.06
    олаг
    -0.06
     bidding
    -0.06
    orough
    -0.06
     mô
    -0.06
    loi
    -0.06
    outh
    -0.06
    POSITIVE LOGITS
    udio
    0.07
    xico
    0.07
    .Assembly
    0.07
    жд
    0.07
     Accuracy
    0.07
    astro
    0.06
    dish
    0.06
     Rap
    0.06
     Pants
    0.06
    strup
    0.06
    Activations Density 0.002%

    No Known Activations