© 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. 40575
    Prev
    Next
    INDEX
    Explanations

    references to company services and qualifications

    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
    ãĥ«ãĥĪ
    -0.07
    uib
    -0.06
    arella
    -0.06
    uteur
    -0.06
    //{{
    -0.06
    arias
    -0.06
    ystone
    -0.06
    óg
    -0.06
     prospect
    -0.06
    /lg
    -0.06
    POSITIVE LOGITS
     online
    0.06
     comprom
    0.06
     agents
    0.06
     åı
    0.06
     TMPro
    0.06
     UK
    0.06
     Editorial
    0.06
    agents
    0.06
    Tester
    0.05
    pha
    0.05
    Activations Density 0.007%

    No Known Activations