© 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. 5-LLAMASCOPE-RES-131K
    6. 126440
    Prev
    Next
    INDEX
    Explanations

    instances of opening or closing parentheses and quotations in the text

    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
    ño
    -0.07
    gran
    -0.07
    ढ
    -0.07
    kest
    -0.06
    ow
    -0.06
    .wr
    -0.06
    Ïĩε
    -0.06
    便
    -0.06
    ÙĪØ¯
    -0.06
    帰
    -0.06
    POSITIVE LOGITS
     rip
    0.07
     given
    0.06
     ÐĿаз
    0.06
    edom
    0.06
    RTOS
    0.06
    ãĥ«ãĥķ
    0.06
    eda
    0.06
     Rip
    0.05
     brides
    0.05
    گاÙĨÛĮ
    0.05
    Activations Density 0.006%

    No Known Activations