© 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. 72195
    Prev
    Next
    INDEX
    Explanations

    instances of the word "modifying."

    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
     Lup
    -0.07
    rade
    -0.07
    -anchor
    -0.07
    είÏĦε
    -0.07
    ember
    -0.07
    /renderer
    -0.07
    anca
    -0.07
    RA
    -0.06
    úa
    -0.06
    æģIJ
    -0.06
    POSITIVE LOGITS
     Grove
    0.07
     initially
    0.06
    á
    0.06
    ingo
    0.06
    Xi
    0.06
    Hmm
    0.05
     originally
    0.05
     Ñĥда
    0.05
    uffman
    0.05
    дал
    0.05
    Activations Density 0.000%

    No Known Activations