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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 89168
    Prev
    Next
    INDEX
    Explanations

    code-related comments and verbose logging statements

    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
    reator
    -0.06
    473
    -0.06
     tackled
    -0.06
    avax
    -0.06
    ory
    -0.06
    çģµ
    -0.06
    tearDown
    -0.06
     ups
    -0.05
    ackages
    -0.05
    rey
    -0.05
    POSITIVE LOGITS
    /debug
    0.10
     level
    0.08
    level
    0.08
    gger
    0.08
    ç²ī
    0.07
    .level
    0.07
    LEVEL
    0.07
    Level
    0.07
    idel
    0.07
    DRV
    0.07
    Activations Density 0.062%

    No Known Activations