© 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. 69493
    Prev
    Next
    INDEX
    Explanations

    indications of performance and progress in various contexts

    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
    OLON
    -0.06
    ETA
    -0.06
    084
    -0.06
    immel
    -0.06
    .scalablytyped
    -0.06
    qa
    -0.06
     Ore
    -0.06
    èĤ²
    -0.06
    esk
    -0.06
     specifications
    -0.05
    POSITIVE LOGITS
     record
    0.12
     Record
    0.10
     records
    0.10
     RECORD
    0.10
    records
    0.09
    -record
    0.09
     Records
    0.09
    record
    0.09
    .record
    0.08
    Record
    0.08
    Activations Density 0.047%

    No Known Activations