© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 40930
    Prev
    Next
    INDEX
    Explanations

    references to formal qualifications or specialized knowledge

    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
    meg
    -0.07
     meg
    -0.07
    omik
    -0.07
    alore
    -0.06
     seg
    -0.06
     Omn
    -0.06
    caffold
    -0.06
    astes
    -0.06
    cade
    -0.06
    zc
    -0.06
    POSITIVE LOGITS
    ãĥ©ãĥ³ãĤ¹
    0.07
     sublic
    0.07
    AccessException
    0.07
     IDirect
    0.06
    -feedback
    0.06
    AGER
    0.06
     sterling
    0.06
    ÙĪÙĨت
    0.06
    اÛĮاÙĨ
    0.06
    aje
    0.06
    Activations Density 0.000%

    No Known Activations