© 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. 128964
    Prev
    Next
    INDEX
    Explanations

    phrases expressing recommendations and trust in service providers

    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
    ergus
    -0.08
    éné
    -0.08
    æ¼
    -0.07
     Vác
    -0.06
    .nih
    -0.06
    gro
    -0.06
    cord
    -0.06
    claimer
    -0.06
    à¸ķลาà¸Ķ
    -0.06
    undry
    -0.06
    POSITIVE LOGITS
     recommend
    0.08
     recommendation
    0.07
    recommend
    0.07
     recommended
    0.07
     Recommend
    0.07
     anytime
    0.07
     Recomm
    0.07
    recommended
    0.07
     recommending
    0.07
    jang
    0.06
    Activations Density 0.009%

    No Known Activations