© 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. 17-LLAMASCOPE-RES-131K
    11. 16543
    Prev
    Next
    INDEX
    Explanations

    formatting and structural elements commonly found in academic writing

    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
    iol
    -0.07
    144
    -0.06
    oda
    -0.06
    .gwt
    -0.06
    agne
    -0.06
     voks
    -0.06
    cout
    -0.06
    quir
    -0.06
     Ø¢Ùħ
    -0.06
    ahat
    -0.06
    POSITIVE LOGITS
     ëħ¼
    0.07
     REFERENCES
    0.07
     Foot
    0.07
    bine
    0.07
     foot
    0.06
     JK
    0.06
     TMPro
    0.06
     laid
    0.06
    adero
    0.06
    ÄįnÃŃk
    0.06
    Activations Density 0.052%

    No Known Activations