© 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. 83045
    Prev
    Next
    INDEX
    Explanations

    terms related to drug production and 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
    ÅĻet
    -0.07
    >Returns
    -0.07
    γή
    -0.07
    ONGL
    -0.07
    822
    -0.06
     costo
    -0.06
    нен
    -0.06
    cms
    -0.06
     frais
    -0.06
    quick
    -0.06
    POSITIVE LOGITS
     cap
    0.07
    ember
    0.07
    eker
    0.06
     quotas
    0.06
    plits
    0.06
     annually
    0.06
    adera
    0.06
    oping
    0.06
     Parties
    0.06
     annual
    0.06
    Activations Density 0.006%

    No Known Activations