© 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. 130858
    Prev
    Next
    INDEX
    Explanations

    technical coding terms related to autoloading and configuration settings

    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
    ando
    -0.08
    oro
    -0.07
    idi
    -0.07
    vas
    -0.06
     Vaugh
    -0.06
    .va
    -0.06
    жÑĥ
    -0.06
     taste
    -0.06
    field
    -0.06
     busy
    -0.06
    POSITIVE LOGITS
    orado
    0.07
    SystemService
    0.07
     sharedApplication
    0.07
    olate
    0.07
    olute
    0.07
    anlık
    0.06
    nici
    0.06
    ÙģتÙĩ
    0.06
    evice
    0.06
     íĬ¹íŀĪ
    0.06
    Activations Density 0.002%

    No Known Activations