© 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. 53933
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence or counts of things

    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
     anything
    -0.07
    anything
    -0.06
    urst
    -0.06
    org
    -0.06
    iid
    -0.06
    one
    -0.06
    au
    -0.06
    mente
    -0.06
    atik
    -0.06
    nze
    -0.05
    POSITIVE LOGITS
    ãĥ«ãĥķ
    0.07
    κÏģα
    0.07
    žÃŃ
    0.06
     èIJ
    0.06
    InstanceState
    0.06
    qui
    0.06
    yre
    0.06
    annel
    0.06
    AGMA
    0.06
    ãĢħ
    0.06
    Activations Density 0.016%

    No Known Activations