© 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. 15-LLAMASCOPE-RES-131K
    11. 86216
    Prev
    Next
    INDEX
    Explanations

    expressions of trust and support in a client-service relationship

    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
    ooter
    -0.07
    _FMT
    -0.06
    èĸ
    -0.06
    och
    -0.06
    uelle
    -0.06
    505
    -0.06
     Furn
    -0.06
     bare
    -0.06
     equ
    -0.05
     contenido
    -0.05
    POSITIVE LOGITS
     client
    0.09
     clients
    0.08
     Client
    0.08
     Clients
    0.08
    ISIBLE
    0.07
    -client
    0.07
    odesk
    0.07
    .client
    0.07
    getClient
    0.07
    Client
    0.07
    Activations Density 0.024%

    No Known Activations