© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26863
    Prev
    Next
    INDEX
    Explanations

    database-related terminology and structures

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     hel
    -0.06
    mx
    -0.06
    æļ´
    -0.06
     Constitutional
    -0.06
    _OVERRIDE
    -0.06
    icerca
    -0.05
    港
    -0.05
    -o
    -0.05
    ilig
    -0.05
    aan
    -0.05
    POSITIVE LOGITS
    wik
    0.07
    eken
    0.07
    ipse
    0.07
    iges
    0.07
    atform
    0.07
     $?
    0.07
    à¹Ħหà¸Ļ
    0.07
    warts
    0.07
    ervlet
    0.07
    à¹Ĩ
    0.07
    Activations Density 0.067%

    No Known Activations