© 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. 28507
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting symbols

    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
    FAIL
    -0.07
    νÏī
    -0.07
    uiten
    -0.06
    zac
    -0.06
    iever
    -0.06
    izik
    -0.06
    ẩu
    -0.06
    illo
    -0.06
    ernel
    -0.06
    loon
    -0.06
    POSITIVE LOGITS
    'gc
    0.07
    edla
    0.06
     Media
    0.06
     media
    0.06
    ickt
    0.06
    -media
    0.06
     PR
    0.06
    roti
    0.06
    Statements
    0.06
     Boo
    0.06
    Activations Density 0.003%

    No Known Activations