© 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. 15-LLAMASCOPE-RES-131K
    11. 86455
    Prev
    Next
    INDEX
    Explanations

    phrases related to errors and inefficiencies in predicting 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
    assi
    -0.07
    oller
    -0.07
     Äijẳng
    -0.06
    _pitch
    -0.06
     oper
    -0.06
     EXCEPTION
    -0.06
    tl
    -0.06
    pitch
    -0.06
    .scalablytyped
    -0.06
     anom
    -0.06
    POSITIVE LOGITS
     correct
    0.07
    iyon
    0.07
    seud
    0.06
     often
    0.06
    nÄĽ
    0.06
    око
    0.06
     sometimes
    0.06
     zbyt
    0.06
     result
    0.06
     Vital
    0.06
    Activations Density 0.042%

    No Known Activations