© 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. 74666
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or confusion regarding opinions and decisions

    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
    io
    -0.06
    if
    -0.06
     Bacon
    -0.06
     perceived
    -0.06
    808
    -0.05
    f
    -0.05
    hp
    -0.05
     (
    -0.05
     not
    -0.05
    Ø´ÙĪر
    -0.05
    POSITIVE LOGITS
    ÑīÑĸ
    0.08
    icros
    0.08
    zia
    0.08
    tdown
    0.08
    obus
    0.08
    (íģ¬ê¸°
    0.07
    HeaderCode
    0.07
    YTE
    0.07
    vetica
    0.07
    orte
    0.07
    Activations Density 0.008%

    No Known Activations