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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90213
    Prev
    Next
    INDEX
    Explanations

    punctuation marks at the end 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
    ibur
    -0.07
    itage
    -0.07
    hurst
    -0.07
    _EOF
    -0.07
    太éĥİ
    -0.07
    boru
    -0.07
    $MESS
    -0.06
    InterfaceOrientation
    -0.06
     seedu
    -0.06
    ulen
    -0.06
    POSITIVE LOGITS
    st
    0.07
     Eis
    0.06
     econ
    0.06
     count
    0.06
    eee
    0.06
    ingle
    0.06
     pron
    0.06
    ennis
    0.05
    quirrel
    0.05
    icial
    0.05
    Activations Density 0.056%

    No Known Activations