© 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. 22-LLAMASCOPE-RES-131K
    6. 4098
    Prev
    Next
    INDEX
    Explanations

    mentions of bankruptcy and related legal processes

    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
    alers
    -0.07
    osy
    -0.07
    جÙĦ
    -0.07
    å¹¹ç·ļ
    -0.07
    unner
    -0.07
     Tome
    -0.07
    kening
    -0.07
    ,exports
    -0.07
    etz
    -0.07
    icans
    -0.07
    POSITIVE LOGITS
    borg
    0.07
    arro
    0.06
    elin
    0.06
    ektiv
    0.06
    EMU
    0.06
    cott
    0.06
    dez
    0.06
     si
    0.06
     Col
    0.05
    786
    0.05
    Activations Density 0.009%

    No Known Activations