Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95645
    Prev
    Next
    INDEX
    Explanations

    numerical values related to viewer ratings and audience metrics

    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
    ISCO
    -0.09
    loh
    -0.08
    eyle
    -0.08
    inand
    -0.07
    reur
    -0.07
    ستÛĮ
    -0.07
    erli
    -0.07
    ά
    -0.07
    ردÙĩ
    -0.07
    oÄį
    -0.07
    POSITIVE LOGITS
    174
    0.06
    ä»ĺãģį
    0.06
     nit
    0.06
     Nit
    0.06
    azine
    0.06
     NSS
    0.06
    880
    0.06
    iss
    0.06
    wert
    0.05
    estone
    0.05
    Activations Density 0.001%

    No Known Activations