© 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. 39651
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, especially colons

    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
     Alam
    -0.06
    ãģ¡ãĤĥãĤĵ
    -0.06
    _Normal
    -0.06
     spiral
    -0.06
     fore
    -0.06
    zel
    -0.06
    atcher
    -0.06
     str
    -0.06
     âĨIJ
    -0.06
     frog
    -0.06
    POSITIVE LOGITS
    odore
    0.07
    utow
    0.07
    EEP
    0.07
    ifestyles
    0.07
    isphere
    0.07
     Weather
    0.07
    .GraphicsUnit
    0.07
    apo
    0.06
    utters
    0.06
    istes
    0.06
    Activations Density 0.001%

    No Known Activations