© 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. 62019
    Prev
    Next
    INDEX
    Explanations

    concepts related to financial transactions and obligations

    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
    izza
    -0.06
    odon
    -0.06
    OfSize
    -0.06
     Alv
    -0.06
    aint
    -0.06
    reste
    -0.06
    ettes
    -0.06
    stal
    -0.06
    Ú©ÙĦ
    -0.06
    agg
    -0.05
    POSITIVE LOGITS
     above
    0.08
    above
    0.07
    .crm
    0.07
    »¿
    0.07
    ileaks
    0.07
     Above
    0.07
     subsequent
    0.07
    kyt
    0.06
     ì²ĺ
    0.06
     subsequently
    0.06
    Activations Density 0.019%

    No Known Activations