© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125132
    Prev
    Next
    INDEX
    Explanations

    instances of conflicting information and contradictions in statements

    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
     darf
    -0.07
     Unexpected
    -0.07
    eros
    -0.07
    erten
    -0.07
    ugu
    -0.07
    Unexpected
    -0.07
    thus
    -0.06
     Appearance
    -0.06
    iche
    -0.06
    alk
    -0.06
    POSITIVE LOGITS
     proven
    0.08
     prov
    0.08
     actually
    0.07
     nowhere
    0.07
     actual
    0.07
     none
    0.07
     repeatedly
    0.07
     nothing
    0.06
     fact
    0.06
     proved
    0.06
    Activations Density 0.062%

    No Known Activations