© 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. 1940
    Prev
    Next
    INDEX
    Explanations

    negations and limitations 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
    rod
    -0.06
    деÑĢж
    -0.06
     tem
    -0.06
    znam
    -0.05
     Malk
    -0.05
     Ch
    -0.05
    abin
    -0.05
     Schwarz
    -0.05
    902
    -0.05
    ace
    -0.05
    POSITIVE LOGITS
    FormatException
    0.07
    itag
    0.07
    reste
    0.07
    tright
    0.07
     ФедеÑĢалÑĮ
    0.07
    Formatted
    0.07
    gan
    0.07
    Äįi
    0.07
     scour
    0.06
    ÙijÙħ
    0.06
    Activations Density 0.007%

    No Known Activations