© 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. 82609
    Prev
    Next
    INDEX
    Explanations

    terms related to academic and professional qualifications or roles

    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
    sei
    -0.06
    ļĮ
    -0.06
    ãĥ¼ãĥł
    -0.05
    ήλ
    -0.05
    ienie
    -0.05
    Sock
    -0.05
    Msp
    -0.05
    Variant
    -0.05
    empo
    -0.05
    eli
    -0.05
    POSITIVE LOGITS
    iverz
    0.07
     Canter
    0.07
     Vegas
    0.07
     Telecom
    0.07
    .hwp
    0.07
    venta
    0.07
    ertino
    0.07
    ILTER
    0.07
    ix
    0.06
     Cork
    0.06
    Activations Density 0.011%

    No Known Activations