© 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. 73773
    Prev
    Next
    INDEX
    Explanations

    references to academic titles and positions

    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
    zsche
    -0.06
    ´
    -0.06
    ervas
    -0.06
     famous
    -0.06
     Harvard
    -0.06
    ossa
    -0.06
    ndx
    -0.06
     Kaplan
    -0.05
     mix
    -0.05
    hart
    -0.05
    POSITIVE LOGITS
    avar
    0.09
    ellen
    0.08
    uge
    0.07
    ascus
    0.07
    _Stream
    0.07
    éĺħ读次æķ°
    0.07
    utex
    0.07
    cción
    0.07
    verity
    0.07
    uga
    0.07
    Activations Density 0.027%

    No Known Activations