© 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. 76271
    Prev
    Next
    INDEX
    Explanations

    information related to medical approvals and vaccine use

    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
     inoc
    -0.06
    аÑĤок
    -0.06
     leak
    -0.06
     poll
    -0.05
    ame
    -0.05
    озд
    -0.05
     Aerospace
    -0.05
     hap
    -0.05
     Scan
    -0.05
     Claw
    -0.05
    POSITIVE LOGITS
     approval
    0.10
     approvals
    0.10
    approval
    0.10
     Approval
    0.09
    yk
    0.09
    Approval
    0.08
    approved
    0.08
     approving
    0.08
     approve
    0.07
    -approved
    0.07
    Activations Density 0.035%

    No Known Activations