© 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 EvalsExportsinterp-engineNEWAPI 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. 39031
    Prev
    Next
    INDEX
    Explanations

    instances of testimony or statements made in a legal context

    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
    ely
    -0.07
    alfa
    -0.07
    ARGE
    -0.07
    cks
    -0.06
    acher
    -0.06
    uste
    -0.06
    ELY
    -0.06
    ¾
    -0.06
    awn
    -0.06
    anou
    -0.06
    POSITIVE LOGITS
    osterone
    0.09
     against
    0.08
     bahwa
    0.07
    Against
    0.07
    /testify
    0.07
    against
    0.07
    imony
    0.07
    enthal
    0.07
    dle
    0.07
    cape
    0.07
    Activations Density 0.004%

    No Known Activations