© 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. 106859
    Prev
    Next
    INDEX
    Explanations

    conditional statements and possibility-related phrases

    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
     пÑĭ
    -0.07
    úng
    -0.07
    td
    -0.07
    ta
    -0.07
    ther
    -0.06
    otta
    -0.06
    azu
    -0.06
    ceed
    -0.06
     hemorrh
    -0.06
    abis
    -0.06
    POSITIVE LOGITS
    illos
    0.07
    aliz
    0.06
     someone
    0.06
    buckets
    0.06
    reuse
    0.06
    zÄĻ
    0.06
    ä½łçļĦ
    0.06
    dech
    0.06
    arl
    0.06
    ologne
    0.06
    Activations Density 0.007%

    No Known Activations