© 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. 106778
    Prev
    Next
    INDEX
    Explanations

    expressions related to honesty and truthfulness

    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
    olk
    -0.08
    è£ķ
    -0.07
    erland
    -0.07
    isko
    -0.07
    å¢
    -0.07
    ÙĬÙĥÙĬ
    -0.07
    olio
    -0.07
     norge
    -0.07
    еÑĢк
    -0.06
    xab
    -0.06
    POSITIVE LOGITS
     itself
    0.06
    wing
    0.06
     sin
    0.06
     Ronald
    0.06
     Sin
    0.06
     pole
    0.06
    iaux
    0.05
     ongoing
    0.05
    gency
    0.05
     Dy
    0.05
    Activations Density 0.000%

    No Known Activations