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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 70436
    Prev
    Next
    INDEX
    Explanations

    words and phrases that convey positivity and favorable qualities about an opportunity or environment

    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
    .Magenta
    -0.08
     Ñĥз
    -0.06
     traf
    -0.06
    ôn
    -0.06
    aptive
    -0.06
    uzey
    -0.06
     sez
    -0.06
    ÙijØ©
    -0.06
    ymi
    -0.06
     Khu
    -0.06
    POSITIVE LOGITS
    xes
    0.07
    нимаÑĤÑĮ
    0.07
    od
    0.06
     Util
    0.06
    lando
    0.06
     Cra
    0.06
    ione
    0.06
    ITO
    0.06
    xing
    0.06
     pew
    0.06
    Activations Density 0.000%

    No Known Activations