© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 17703
    Prev
    Next
    INDEX
    Explanations

    terms associated with actions involving construction, modeling, or programming

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     via
    -0.06
    779
    -0.06
     by
    -0.06
     cez
    -0.06
     Ñģобой
    -0.06
     Bent
    -0.05
    lining
    -0.05
     Scre
    -0.05
     Seed
    -0.05
     unlikely
    -0.05
    POSITIVE LOGITS
     away
    0.09
     Away
    0.08
    Away
    0.08
    κÏģα
    0.08
    ToFront
    0.08
    iá»ĥu
    0.08
    away
    0.08
    dek
    0.07
    -away
    0.07
    STS
    0.07
    Activations Density 0.059%

    No Known Activations