© 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. 17-LLAMASCOPE-RES-131K
    11. 106342
    Prev
    Next
    INDEX
    Explanations

    punctuation, specifically periods

    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
    chain
    -0.07
    amat
    -0.07
    openhagen
    -0.07
    erosis
    -0.07
    weit
    -0.06
    lite
    -0.06
    ieren
    -0.06
     chain
    -0.06
     fur
    -0.06
    문
    -0.06
    POSITIVE LOGITS
    elic
    0.06
    urg
    0.06
    illy
    0.06
     ancest
    0.06
    -lang
    0.06
     Aw
    0.06
    JKLMNOP
    0.06
    æĹıèĩªæ²»
    0.06
    pcs
    0.06
     Awakening
    0.06
    Activations Density 0.003%

    No Known Activations