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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 120705
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or qualifications regarding claims and behaviors

    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
    álido
    -0.07
    ç¾½
    -0.07
    rey
    -0.07
    женÑĮ
    -0.07
    ongyang
    -0.07
    apot
    -0.07
    abra
    -0.07
    sWith
    -0.06
    üven
    -0.06
     гÑĢо
    -0.06
    POSITIVE LOGITS
     anymore
    0.07
     necessarily
    0.07
     it
    0.07
    Å¡ek
    0.06
     ull
    0.06
    licas
    0.06
    )NULL
    0.06
    éĤ£ä¹Ī
    0.06
    à¹Įà¹Ĥ
    0.06
    éĤĦ
    0.05
    Activations Density 0.004%

    No Known Activations