© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61690
    Prev
    Next
    INDEX
    Explanations

    specific data points or metrics related to legal or corporate structures

    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
    -0.07
    ewis
    -0.07
    .AWS
    -0.07
    astered
    -0.07
    ìĬ¤íĦ°
    -0.06
    ipop
    -0.06
    acyj
    -0.06
    swick
    -0.06
    oster
    -0.06
    änn
    -0.06
    POSITIVE LOGITS
    jobs
    0.07
     Citation
    0.07
     Casual
    0.06
     Nash
    0.06
     employment
    0.06
    acas
    0.06
    employment
    0.06
     Beauty
    0.06
    antas
    0.06
    ullo
    0.06
    Activations Density 0.000%

    No Known Activations