© 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. 78524
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "first" along with ordinal numbers

    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
    contri
    -0.07
    itone
    -0.06
    ãģ«åĩº
    -0.06
     spare
    -0.06
    ifen
    -0.06
    irsch
    -0.06
    bersome
    -0.06
    lys
    -0.06
    ãĥªãĤ¹
    -0.06
    unkt
    -0.06
    POSITIVE LOGITS
    -ever
    0.09
     ever
    0.09
    ever
    0.08
    alink
    0.06
    Ever
    0.06
    uron
    0.06
     taste
    0.06
    st
    0.06
    太éĥİ
    0.06
    ynet
    0.06
    Activations Density 0.010%

    No Known Activations