© 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. 71609
    Prev
    Next
    INDEX
    Explanations

    phrases related to advice and collaboration

    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
    rowse
    -0.07
    dump
    -0.07
    ÏĦει
    -0.07
    readcr
    -0.07
    onis
    -0.07
    ooks
    -0.06
    ÑĢаÑĩ
    -0.06
     Pron
    -0.06
    çħ§
    -0.06
    ắp
    -0.06
    POSITIVE LOGITS
     understands
    0.08
    äºĨ解
    0.07
     directly
    0.07
     knows
    0.07
     know
    0.07
     understanding
    0.07
    know
    0.07
     experience
    0.07
     ties
    0.06
     KNOW
    0.06
    Activations Density 0.024%

    No Known Activations