© 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. 15-LLAMASCOPE-RES-131K
    11. 90353
    Prev
    Next
    INDEX
    Explanations

    elements of uncertainty or clarification 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
     ex
    -0.06
    å¯Ħ
    -0.06
    reh
    -0.05
     foreign
    -0.05
     Coin
    -0.05
     coin
    -0.05
    ini
    -0.05
    I
    -0.05
     national
    -0.05
    Âł
    -0.05
    POSITIVE LOGITS
    Ñħи
    0.10
    WND
    0.09
    precated
    0.08
     paran
    0.08
    ervo
    0.08
    ï¼
    0.08
     POSSIBILITY
    0.08
    persistent
    0.08
    LOCITY
    0.08
    uforia
    0.08
    Activations Density 0.010%

    No Known Activations