© 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. 89592
    Prev
    Next
    INDEX
    Explanations

    words related to the significance and quality of experiences or objects

    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
    quelle
    -0.07
    mares
    -0.07
    hor
    -0.06
     Shepard
    -0.06
    oog
    -0.06
    cid
    -0.06
    atoes
    -0.06
    adi
    -0.06
    123
    -0.06
    rupted
    -0.06
    POSITIVE LOGITS
    chez
    0.08
    swer
    0.08
    iÄįe
    0.07
    isex
    0.07
     Huff
    0.07
    ãĥ³ãĤ¬
    0.07
     Webseite
    0.07
    -toolbar
    0.07
     kostenlose
    0.06
    elman
    0.06
    Activations Density 0.043%

    No Known Activations