© 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. 5-LLAMASCOPE-RES-131K
    11. 126662
    Prev
    Next
    INDEX
    Explanations

    references to funding and financial commitments

    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
    ingly
    -0.08
    oley
    -0.07
    aleza
    -0.07
    gba
    -0.07
    缮ãģ®
    -0.07
    weis
    -0.06
    ongo
    -0.06
    hra
    -0.06
    stein
    -0.06
    .pres
    -0.06
    POSITIVE LOGITS
    atest
    0.07
    ãĥ©ãĥ³
    0.06
    het
    0.06
    oproject
    0.06
    رÛĮÙĩ
    0.06
    467
    0.06
     اÙĦخط
    0.06
    emme
    0.06
    à¸Ł
    0.06
    lander
    0.06
    Activations Density 0.018%

    No Known Activations