© 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. 75840
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas, indicating the structure of sentences

    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
    mpp
    -0.07
    affle
    -0.07
    obuf
    -0.07
    _DEPEND
    -0.07
    ERVED
    -0.07
    urum
    -0.06
    &C
    -0.06
    ulner
    -0.06
     Matth
    -0.06
    جÙĦ
    -0.06
    POSITIVE LOGITS
    ikh
    0.08
     whose
    0.07
     ref
    0.06
     meantime
    0.06
     already
    0.06
    é¹
    0.06
     refs
    0.06
     predict
    0.06
     hel
    0.06
     Ars
    0.06
    Activations Density 0.015%

    No Known Activations