© 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. 95027
    Prev
    Next
    INDEX
    Explanations

    content related to mathematical or programming concepts

    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
    cdb
    -0.07
     Stick
    -0.07
    ophil
    -0.07
    Stick
    -0.07
    agma
    -0.07
    oons
    -0.07
    stud
    -0.07
     stick
    -0.07
    å·
    -0.07
    uran
    -0.07
    POSITIVE LOGITS
     Carb
    0.07
     Muss
    0.07
    amos
    0.06
    à¹Ģหà¸Ļ
    0.06
     Enterprise
    0.06
     defe
    0.06
     ?:
    0.06
    sin
    0.06
     Carmen
    0.06
     Maiden
    0.05
    Activations Density 0.060%

    No Known Activations