© 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 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. 78549
    Prev
    Next
    INDEX
    Explanations

    references to customer contracts and legal agreements within the context of a service or product

    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
    iten
    -0.06
    iden
    -0.06
    omore
    -0.06
     Pool
    -0.06
    atal
    -0.05
    vÄĽdom
    -0.05
    _altern
    -0.05
    DW
    -0.05
     inc
    -0.05
    USA
    -0.05
    POSITIVE LOGITS
     existing
    0.13
     already
    0.12
    -existing
    0.10
     Existing
    0.10
     grandfather
    0.10
    Existing
    0.10
    existing
    0.09
    æŧ
    0.09
     legacy
    0.09
    legacy
    0.09
    Activations Density 0.017%

    No Known Activations