© 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. 17-LLAMASCOPE-RES-131K
    11. 75659
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to injunctions and passing off cases

    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
     district
    -0.06
     prod
    -0.06
    haar
    -0.06
    nbr
    -0.06
    _zones
    -0.06
    ãĤ
    -0.06
     omp
    -0.06
    ilers
    -0.05
    nier
    -0.05
    addin
    -0.05
    POSITIVE LOGITS
    ignum
    0.07
    åĭ
    0.07
    roy
    0.07
    аÑĤом
    0.07
    ré
    0.07
    樹
    0.06
    Had
    0.06
    iji
    0.06
     vign
    0.06
    orch
    0.06
    Activations Density 0.050%

    No Known Activations