© 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. 70378
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and research

    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
    ught
    -0.08
    ug
    -0.07
    ancer
    -0.06
    lassen
    -0.06
    istrovstvÃŃ
    -0.06
    wit
    -0.06
    794
    -0.06
    ÅĤ
    -0.06
    Bearer
    -0.05
    ilk
    -0.05
    POSITIVE LOGITS
     conducted
    0.09
    buz
    0.08
     findings
    0.07
     participants
    0.07
     involving
    0.07
    ãĥ¬ãĥ¼
    0.07
    orz
    0.07
     NotSupportedException
    0.06
    à¸ī
    0.06
     published
    0.06
    Activations Density 0.014%

    No Known Activations