© 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. 71428
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to regulatory or legal frameworks

    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
    ãĥ¼ãĤ¿
    -0.07
    ãĤĩ
    -0.07
    anko
    -0.06
    Knife
    -0.06
    纪
    -0.06
    ãĥ¥ãĥ¼
    -0.06
    axed
    -0.06
    verbosity
    -0.06
     lia
    -0.06
    øy
    -0.06
    POSITIVE LOGITS
     abbreviated
    0.08
    abbrev
    0.08
     acronym
    0.06
     اختص
    0.06
    arkin
    0.06
    LEV
    0.06
    alin
    0.06
    887
    0.06
    رÙĪÙĩ
    0.06
    ÙĪرش
    0.06
    Activations Density 0.041%

    No Known Activations