© 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. 14593
    Prev
    Next
    INDEX
    Explanations

    academic and formal writing structures

    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
    æ²¢
    -0.07
    [d
    -0.07
    ãĥªãĤ«
    -0.06
    /apis
    -0.06
     Crimes
    -0.06
    deg
    -0.06
     Avg
    -0.06
     Barton
    -0.06
     Rif
    -0.06
     Barth
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
    uzzi
    0.07
    OrDefault
    0.07
    ãĤ¹ãĤ¿ãĥ¼
    0.06
    hlen
    0.06
    audi
    0.06
     into
    0.06
    cole
    0.06
    oram
    0.06
    pta
    0.06
    Activations Density 0.065%

    No Known Activations