© 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. 120407
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting commonly associated with web content and online resources

    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
    ãĤ¤ãĥī
    -0.06
    ARSER
    -0.06
    ży
    -0.06
    ixo
    -0.06
     âĢŀ
    -0.06
    Helper
    -0.06
     "_
    -0.06
    ÙıÙĪÙĨ
    -0.06
    çĦ¡ãģĹ
    -0.06
     ãĥ»
    -0.06
    POSITIVE LOGITS
    akit
    0.07
     ÑĤоÑīо
    0.07
     Uncategorized
    0.07
     etc
    0.07
     inexpensive
    0.06
    uw
    0.06
    coon
    0.06
    Ñĥнк
    0.06
    itemap
    0.06
    utterstock
    0.06
    Activations Density 0.022%

    No Known Activations