© 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. 53935
    Prev
    Next
    INDEX
    Explanations

    descriptors indicating quality and related attributes in a professional or personal context

    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
    ocker
    -0.07
    stands
    -0.06
    ç¶
    -0.06
    lok
    -0.06
    akis
    -0.06
    ionic
    -0.06
    uth
    -0.06
    наÑĢ
    -0.06
     sheds
    -0.06
    ниÑģÑĤ
    -0.06
    POSITIVE LOGITS
     ways
    0.07
    ivent
    0.07
     stuff
    0.07
     pig
    0.07
    wor
    0.07
    iedo
    0.06
    allee
    0.06
     Hud
    0.06
    iglia
    0.06
    ity
    0.06
    Activations Density 0.154%

    No Known Activations