© 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. 128960
    Prev
    Next
    INDEX
    Explanations

    references to the United States in various contexts

    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
    ivar
    -0.07
    xious
    -0.06
    225
    -0.06
    anian
    -0.06
     Lancaster
    -0.06
     Gott
    -0.06
       
    -0.06
    обÑĢеÑĤ
    -0.06
    eker
    -0.06
    ker
    -0.06
    POSITIVE LOGITS
    raž
    0.06
    (es
    0.06
    lemn
    0.06
    #__
    0.06
    405
    0.06
    roz
    0.06
    asma
    0.06
    MC
    0.06
    ,'#
    0.06
    hes
    0.06
    Activations Density 0.020%

    No Known Activations