© 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. 126423
    Prev
    Next
    INDEX
    Explanations

    references to purchasing drugs, specifically soma

    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
    isto
    -0.06
     which
    -0.06
     Libert
    -0.06
     stands
    -0.05
     m
    -0.05
    kest
    -0.05
    chap
    -0.05
     pay
    -0.05
     Patel
    -0.05
    hl
    -0.05
    POSITIVE LOGITS
    ãĥ³ãĤº
    0.08
    ãĥ¥ãĥ¼
    0.08
     mül
    0.07
    anst
    0.07
    Ỽp
    0.07
    .poster
    0.07
    ogs
    0.07
    pls
    0.07
    наÑĤ
    0.07
     DISCLAIM
    0.07
    Activations Density 0.002%

    No Known Activations