© 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. 84539
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the receipt or acquisition of items or experiences

    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
    allery
    -0.08
    aka
    -0.08
    ака
    -0.07
    олÑĮно
    -0.07
    lobal
    -0.07
    ij¸
    -0.07
    ilight
    -0.07
     Danh
    -0.07
    ano
    -0.07
     пÑĢоÑħ
    -0.07
    POSITIVE LOGITS
     to
    0.07
    rise
    0.06
    bread
    0.06
     opportunity
    0.06
     chance
    0.06
     a
    0.06
     benefit
    0.06
    stad
    0.05
     Kum
    0.05
     access
    0.05
    Activations Density 0.024%

    No Known Activations