© 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. 103604
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    End parts of proper names or identifiers appearing in lists, bibliographic citations, menu items, or structured data collections.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ohl
    -0.07
    lesia
    -0.07
    quiry
    -0.07
    ãĤ·ãĤ¢
    -0.07
    olet
    -0.07
    UPER
    -0.07
    ï¸
    -0.06
     tuz
    -0.06
    idor
    -0.06
    æº
    -0.06
    POSITIVE LOGITS
     aforementioned
    0.07
     again
    0.07
    mentioned
    0.07
    Question
    0.06
    again
    0.06
    ADIO
    0.06
     mentioned
    0.06
    çµĮ
    0.06
     Again
    0.06
    atto
    0.06
    Activations Density 0.025%

    No Known Activations