© 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. 80974
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or potential outcomes

    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
    cai
    -0.07
    εβ
    -0.07
     READY
    -0.07
    åħ¬è·¯
    -0.06
    _READY
    -0.06
     rebel
    -0.06
     oÄįek
    -0.06
     æ¼
    -0.06
    amik
    -0.06
     Rebel
    -0.06
    POSITIVE LOGITS
    zel
    0.07
    oyer
    0.07
    dea
    0.07
    ede
    0.06
    fila
    0.06
    enze
    0.06
     space
    0.06
    961
    0.06
    aley
    0.06
    ufen
    0.06
    Activations Density 0.002%

    No Known Activations