© 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. 89853
    Prev
    Next
    INDEX
    Explanations

    promotional offers and membership details

    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
    leo
    -0.07
    宿
    -0.07
    Âİ
    -0.06
    OutOf
    -0.06
     distributions
    -0.06
    acer
    -0.06
    ikk
    -0.06
    -nil
    -0.06
    ãĥĪãĥ«
    -0.06
    lava
    -0.06
    POSITIVE LOGITS
     memberships
    0.10
     Membership
    0.09
     membership
    0.09
    membership
    0.09
    Membership
    0.08
     gym
    0.08
     club
    0.08
     fee
    0.08
     facility
    0.08
    club
    0.07
    Activations Density 0.008%

    No Known Activations