© 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. 56470
    Prev
    Next
    INDEX
    Explanations

    terms related to medical testing and procedures

    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
    OD
    -0.06
     ev
    -0.06
    rej
    -0.06
     pal
    -0.06
     id
    -0.06
    aram
    -0.06
    619
    -0.05
    od
    -0.05
     Seiten
    -0.05
    ussen
    -0.05
    POSITIVE LOGITS
    itest
    0.07
    ires
    0.07
    gos
    0.07
    Integral
    0.07
    endale
    0.07
    immel
    0.07
     dilig
    0.06
     Declaration
    0.06
    nul
    0.06
    quito
    0.06
    Activations Density 0.006%

    No Known Activations