© 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. 103657
    Prev
    Next
    INDEX
    Explanations

    financial and investment-related terminology

    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
    assandra
    -0.08
    cki
    -0.07
    ely
    -0.07
    raç
    -0.07
    olio
    -0.07
    tas
    -0.07
    лаÑĩ
    -0.07
    å¥ī
    -0.07
    оваÑĢ
    -0.07
    zos
    -0.07
    POSITIVE LOGITS
     during
    0.08
    oter
    0.08
    uteur
    0.07
     Arg
    0.06
     Energ
    0.06
    cob
    0.06
    during
    0.06
     ent
    0.06
     when
    0.06
     throughout
    0.06
    Activations Density 0.003%

    No Known Activations