© 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. 96005
    Prev
    Next
    INDEX
    Explanations

    terms related to preparation and planning processes

    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
    ala
    -0.07
    apon
    -0.07
    atoi
    -0.07
    ŀ
    -0.07
    olas
    -0.07
     Karlov
    -0.06
    quier
    -0.06
    plex
    -0.06
    oleon
    -0.06
    ura
    -0.06
    POSITIVE LOGITS
    ForSegue
    0.11
    -made
    0.08
    ness
    0.08
    ares
    0.07
    iegel
    0.07
     groundwork
    0.07
    374
    0.07
    -ahead
    0.07
    igs
    0.06
    ToShow
    0.06
    Activations Density 0.020%

    No Known Activations