© 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 EvalsExportsAPI 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. 75062
    Prev
    Next
    INDEX
    Explanations

    variations of the word "catalogue."

    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
    каÑģ
    -0.08
    ilde
    -0.07
    akin
    -0.07
    Äįet
    -0.07
    estone
    -0.07
    icap
    -0.07
    ÑģÑı
    -0.07
    ept
    -0.07
    orest
    -0.07
    toa
    -0.07
    POSITIVE LOGITS
    .scalablytyped
    0.07
    OT
    0.06
     aff
    0.06
    алÑĥ
    0.06
    DBC
    0.06
     world
    0.06
     pie
    0.06
    èĥ¶
    0.05
     Sanct
    0.05
    441
    0.05
    Activations Density 0.001%

    No Known Activations