© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128972
    Prev
    Next
    INDEX
    Explanations

    references to storytelling and narratives

    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
    reet
    -0.07
    enza
    -0.07
    568
    -0.07
     Trie
    -0.07
    ãģĭãĤı
    -0.06
     Westbrook
    -0.06
    çͳ
    -0.06
    ierrez
    -0.06
     remainder
    -0.06
    lum
    -0.06
    POSITIVE LOGITS
     ones
    0.11
     Ones
    0.09
    ones
    0.08
     greatest
    0.08
     often
    0.08
     those
    0.07
     Often
    0.07
    Often
    0.07
    egas
    0.07
     tend
    0.07
    Activations Density 0.028%

    No Known Activations