© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91612
    Prev
    Next
    INDEX
    Explanations

    references to subjective experiences or opinions about media and events

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Past tense verbs (like "seen", "heard", "had") following superlative expressions that indicate personal experience or evaluation, such as "best I've", "one of the best I've", or similar constructions.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered by @lu-christina
    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
    Negative Logits
    ounge
    -0.08
    ULO
    -0.07
    мени
    -0.07
    ulia
    -0.06
     instead
    -0.06
    getter
    -0.06
    ürn
    -0.06
    eurs
    -0.06
    .dy
    -0.06
    uling
    -0.06
    POSITIVE LOGITS
     anywhere
    0.10
     ever
    0.10
    ä¹ĭä¸Ģ
    0.09
    ever
    0.09
     jamais
    0.08
     EVER
    0.08
     lately
    0.08
     vůbec
    0.08
    loha
    0.07
    -ever
    0.07
    Activations Density 0.008%

    No Known Activations