© 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. 104048
    Prev
    Next
    INDEX
    Explanations

    technical specifications and historical details of firearms

    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
    -0.07
    ă
    -0.07
     Madden
    -0.06
    guard
    -0.06
    idi
    -0.06
    âĢİ
    -0.06
    âĢ¦.
    -0.05
     fucking
    -0.05
     incentiv
    -0.05
     delic
    -0.05
    POSITIVE LOGITS
    uppen
    0.08
    .shader
    0.08
    ãĥ¬ãĥĥãĥĪ
    0.07
    ç©´
    0.07
    antt
    0.07
    ì§ĢëıĦ
    0.07
    нимаеÑĤ
    0.07
    ilestone
    0.07
    çIJ´
    0.07
    anlı
    0.07
    Activations Density 0.005%

    No Known Activations