© 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. 15-LLAMASCOPE-RES-131K
    11. 86069
    Prev
    Next
    INDEX
    Explanations

    phrases indicating perceptions or judgments about situations or events

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    سد
    -0.07
     Harding
    -0.07
    arie
    -0.07
     çĨ
    -0.07
    eph
    -0.07
    ìĬµ
    -0.07
    osti
    -0.06
    UCK
    -0.06
     hå
    -0.06
    autos
    -0.06
    POSITIVE LOGITS
    Ñģли
    0.07
    íĨ
    0.06
    ylon
    0.06
    herits
    0.06
    tm
    0.06
    avern
    0.06
    IPA
    0.06
     perceived
    0.06
    370
    0.05
    olicy
    0.05
    Activations Density 0.005%

    No Known Activations