© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70057
    Prev
    Next
    INDEX
    Explanations

    phrases indicating approval, safety, and condition of services

    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
    amic
    -0.07
    rier
    -0.07
    shal
    -0.07
    rescia
    -0.07
    enga
    -0.07
    arro
    -0.07
    opyright
    -0.06
    ubic
    -0.06
    ign
    -0.06
    ød
    -0.06
    POSITIVE LOGITS
    ritz
    0.07
    Äįan
    0.06
    Ùħت
    0.06
    ãĥ¼ãĥĩ
    0.06
     pand
    0.06
    =search
    0.06
    _locator
    0.06
     Bach
    0.06
     nữa
    0.06
    Äįin
    0.06
    Activations Density 0.003%

    No Known Activations