© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 105535
    Prev
    Next
    INDEX
    Explanations

    decimal numbers and punctuation marks within numeric contexts

    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
     D
    -0.06
    omp
    -0.06
    bourne
    -0.06
     Fr
    -0.06
    FR
    -0.06
    aper
    -0.06
    é
    -0.06
     soph
    -0.06
    lena
    -0.06
    olson
    -0.05
    POSITIVE LOGITS
    Ħĸ
    0.07
    ogonal
    0.07
     voks
    0.07
    laÅŁ
    0.07
    uger
    0.07
    _weak
    0.07
    WXYZ
    0.07
    _heading
    0.07
    _TAC
    0.06
     Primitive
    0.06
    Activations Density 0.006%

    No Known Activations