© 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. 70136
    Prev
    Next
    INDEX
    Explanations

    references to a specific mathematical work or author

    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
    abase
    -0.08
    Fi
    -0.06
    queda
    -0.06
     Enlightenment
    -0.06
    olute
    -0.06
     recently
    -0.06
    .IS
    -0.06
     Recently
    -0.06
    inoa
    -0.06
    arah
    -0.06
    POSITIVE LOGITS
    196
    0.17
    197
    0.14
    195
    0.13
    194
    0.12
    198
    0.10
    193
    0.10
    192
    0.08
    189
    0.08
    Û±Û¹Û¶
    0.08
    188
    0.07
    Activations Density 0.068%

    No Known Activations