© 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. 29619
    Prev
    Next
    INDEX
    Explanations

    phrases associated with customer service and issue resolution

    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
    ptom
    -0.07
    EMY
    -0.07
    Indented
    -0.07
    zend
    -0.06
    ibaba
    -0.06
     vin
    -0.06
    andin
    -0.06
    itty
    -0.06
     Extension
    -0.06
    /backend
    -0.06
    POSITIVE LOGITS
    oggler
    0.07
    боÑĤ
    0.07
     quelque
    0.07
    ä»»ä½ķ
    0.07
    ãĥ¼ãĥ©
    0.07
    something
    0.07
     iets
    0.06
    odore
    0.06
    miss
    0.06
     ANY
    0.06
    Activations Density 0.012%

    No Known Activations