© 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. 15-LLAMASCOPE-RES-131K
    11. 90453
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer engagement and interaction

    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
    uma
    -0.07
    uthor
    -0.06
    olley
    -0.06
    ews
    -0.06
    uitka
    -0.06
    å¸ĸ
    -0.06
     eldre
    -0.06
     Pu
    -0.06
    jeta
    -0.06
    顶
    -0.06
    POSITIVE LOGITS
     reader
    0.08
     readers
    0.08
     everyone
    0.08
    大家
    0.08
     customers
    0.08
     anyone
    0.08
    çĶ¨æĪ·
    0.07
     everybody
    0.07
     consumers
    0.07
     anybody
    0.07
    Activations Density 0.289%

    No Known Activations