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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3258
    Prev
    Next
    INDEX
    Explanations

    issues related to maintenance and repair of systems or mechanical parts

    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
    illez
    -0.07
    rvé
    -0.07
    _BUCKET
    -0.07
    otta
    -0.07
    engine
    -0.07
    886
    -0.07
    erties
    -0.07
    ohn
    -0.06
    .SERVER
    -0.06
     validationResult
    -0.06
    POSITIVE LOGITS
     duty
    0.07
     malfunction
    0.06
    arov
    0.06
    anner
    0.06
     usage
    0.06
     Duty
    0.06
     functionality
    0.06
     fail
    0.06
    PointCloud
    0.06
     misuse
    0.06
    Activations Density 0.061%

    No Known Activations