© 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. 5-LLAMASCOPE-RES-131K
    11. 125766
    Prev
    Next
    INDEX
    Explanations

    various conjunctions and punctuation that denote lists or sequences

    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
    imits
    -0.07
    acco
    -0.07
    ONGL
    -0.06
    rote
    -0.06
    eur
    -0.06
    ammed
    -0.06
    Sharper
    -0.06
    acades
    -0.06
    thinkable
    -0.06
    æŀľ
    -0.06
    POSITIVE LOGITS
    lev
    0.07
    ERT
    0.06
    always
    0.06
     lev
    0.06
    Ïĩη
    0.06
    etine
    0.06
    ãĥ«ãĥĪ
    0.06
    infeld
    0.06
     scaled
    0.06
    .wik
    0.06
    Activations Density 0.002%

    No Known Activations