© 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. 38254
    Prev
    Next
    INDEX
    Explanations

    references to visual or art-related content

    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
    ifen
    -0.07
     vista
    -0.06
    ospel
    -0.06
    enga
    -0.06
    119
    -0.06
     воÑĤ
    -0.06
     adel
    -0.06
    erot
    -0.06
    ominator
    -0.06
    ute
    -0.05
    POSITIVE LOGITS
    /on
    0.09
    -mf
    0.07
    ept
    0.07
    xAE
    0.07
     reck
    0.07
    íĥķ
    0.07
    osu
    0.06
     sworn
    0.06
    FM
    0.06
    ilibrium
    0.06
    Activations Density 0.043%

    No Known Activations