© 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. 60807
    Prev
    Next
    INDEX
    Explanations

    terms associated with insider trading activities

    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
    ertz
    -0.07
    phinx
    -0.07
    ingga
    -0.07
    bern
    -0.07
    uentes
    -0.07
    ÑĨÑĮ
    -0.07
    á»ijt
    -0.07
    steps
    -0.06
    azio
    -0.06
    incerely
    -0.06
    POSITIVE LOGITS
     cop
    0.06
    aton
    0.06
    shares
    0.06
     Moran
    0.06
     shares
    0.06
     Mor
    0.06
     Oro
    0.06
    [--
    0.06
     morale
    0.06
     CES
    0.06
    Activations Density 0.001%

    No Known Activations