© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56819
    Prev
    Next
    INDEX
    Explanations

    phrases related to distinguishing fact from fiction

    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
    Ñģол
    -0.08
    eum
    -0.08
    rž
    -0.08
    ICAST
    -0.08
    alf
    -0.08
    eut
    -0.08
    rám
    -0.08
    SURE
    -0.08
    peÄį
    -0.08
    âĢ¦"↵↵
    -0.07
    POSITIVE LOGITS
     everything
    0.07
     quot
    0.06
    /of
    0.05
     ÑģобоÑİ
    0.05
     reality
    0.05
     increasingly
    0.05
    /or
    0.05
    ernet
    0.05
     ideology
    0.05
     logos
    0.05
    Activations Density 0.039%

    No Known Activations