© 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. 87495
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific punctuation marks and the word "United."

    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
    otas
    -0.07
    olit
    -0.07
    oti
    -0.06
    ITO
    -0.06
    ůj
    -0.06
    plib
    -0.06
    olet
    -0.06
    klad
    -0.06
    lobe
    -0.06
    ãģ¡ãĤī
    -0.06
    POSITIVE LOGITS
    caret
    0.07
    ayan
    0.07
    ëĭĺìĿ´
    0.06
     CDDL
    0.06
    odash
    0.06
    :params
    0.06
    gro
    0.06
    assandra
    0.06
    Ace
    0.06
     drafts
    0.06
    Activations Density 0.004%

    No Known Activations