© 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. 62144
    Prev
    Next
    INDEX
    Explanations

    references to financial institutions and government programs associated with economics and social welfare

    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
     Buna
    -0.07
    æĤ
    -0.07
     sublicense
    -0.06
    Iterable
    -0.06
    ifu
    -0.06
     Ná
    -0.06
    ingular
    -0.06
    ÑĢим
    -0.06
    -dismiss
    -0.06
    ëŁī
    -0.06
    POSITIVE LOGITS
    jang
    0.07
    holm
    0.07
     continued
    0.07
     continuation
    0.07
    ży
    0.07
     пал
    0.06
    inae
    0.06
    ropol
    0.06
     Ye
    0.06
    ivial
    0.06
    Activations Density 0.019%

    No Known Activations