© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106055
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical drug names and their classifications

    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
    iple
    -0.07
    Ñıг
    -0.07
    .Operator
    -0.06
     Stateless
    -0.06
     obr
    -0.06
    /projects
    -0.06
    onne
    -0.06
     Loot
    -0.06
    itage
    -0.06
    adas
    -0.06
    POSITIVE LOGITS
     brands
    0.08
    ramer
    0.07
     brand
    0.07
     popular
    0.06
     Lilly
    0.06
    avor
    0.06
     commonly
    0.06
    brand
    0.06
    _AVAILABLE
    0.06
    -family
    0.06
    Activations Density 0.019%

    No Known Activations