© 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. 53821
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ongoing reporting or commentary on a subject

    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
    enci
    -0.06
    linger
    -0.06
    obel
    -0.06
     dizzy
    -0.05
     &
    -0.05
     ultimately
    -0.05
    to
    -0.05
    amel
    -0.05
    fd
    -0.05
     paradox
    -0.05
    POSITIVE LOGITS
    -scrollbar
    0.07
    олÑĥÑĩ
    0.07
     LOL
    0.07
    æ¡IJ
    0.07
    æŁĦ
    0.07
    -metadata
    0.07
    ReLU
    0.07
    sage
    0.07
    (DWORD
    0.07
    NSSet
    0.07
    Activations Density 0.001%

    No Known Activations