© 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 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. 9-LLAMASCOPE-RES-131K
    11. 97167
    Prev
    Next
    INDEX
    Explanations

    specialized terminology and complex phrasing related to various fields

    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
     Decomp
    -0.06
    asca
    -0.06
    (er
    -0.06
    etik
    -0.06
    è¨İ
    -0.06
     Huntington
    -0.06
    illery
    -0.05
     Ðŀк
    -0.05
    ture
    -0.05
    PostBack
    -0.05
    POSITIVE LOGITS
    .blogspot
    0.09
    Å¡ak
    0.08
    ré
    0.07
    atre
    0.07
    -than
    0.06
     Baghd
    0.06
    ÑģÑıÑĩ
    0.06
    echa
    0.06
    bid
    0.06
    ucch
    0.06
    Activations Density 0.051%

    No Known Activations