© 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. 31143
    Prev
    Next
    INDEX
    Explanations

    technical or engineering processes

    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
    .scalablytyped
    -0.08
    åłĤ
    -0.07
    egie
    -0.07
    Traits
    -0.06
    ucha
    -0.06
    raig
    -0.06
    igner
    -0.06
    pton
    -0.06
    gregator
    -0.06
    useppe
    -0.06
    POSITIVE LOGITS
     technical
    0.09
     Technical
    0.08
     diagnostic
    0.08
    çİ°åľº
    0.08
     diagn
    0.08
     Parts
    0.07
    è¯Ĭ
    0.07
     training
    0.07
     spare
    0.07
    Technical
    0.07
    Activations Density 0.022%

    No Known Activations