© 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. 129146
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer engagement and information requests

    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
    èī
    -0.07
    ream
    -0.06
    ancell
    -0.06
     Contrast
    -0.06
    ãĥ¼ãĥIJ
    -0.06
     mon
    -0.06
    cheap
    -0.06
     Council
    -0.06
    _msgs
    -0.05
    stadt
    -0.05
    POSITIVE LOGITS
    æ´
    0.09
     Chat
    0.08
     chat
    0.08
    Chat
    0.07
     contact
    0.07
    /chat
    0.07
    chat
    0.07
    mgr
    0.06
    lags
    0.06
    enne
    0.06
    Activations Density 0.022%

    No Known Activations