© 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. 22-LLAMASCOPE-RES-131K
    11. 4242
    Prev
    Next
    INDEX
    Explanations

    language related to generic drug approvals and pharmaceutical regulation

    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
    rah
    -0.07
     Zuk
    -0.06
    Wire
    -0.06
     Wire
    -0.06
    .instrument
    -0.06
    軽
    -0.06
    ulus
    -0.06
    راÙģ
    -0.06
     extremes
    -0.06
    angled
    -0.06
    POSITIVE LOGITS
     generic
    0.12
     generics
    0.11
    generic
    0.10
     Generic
    0.10
    Generic
    0.10
    -generic
    0.09
     GENERIC
    0.08
     brand
    0.08
    eneric
    0.08
    .generic
    0.08
    Activations Density 0.013%

    No Known Activations