© 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. 85953
    Prev
    Next
    INDEX
    Explanations

    mentions of judicial reviews and court rulings

    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
    .addTarget
    -0.08
    çĥĪ
    -0.08
    mobx
    -0.07
     plav
    -0.07
    å±±å¸Ĥ
    -0.07
    å¾ĭ
    -0.07
    ãĤ¢ãĥ³
    -0.07
    ucha
    -0.07
    _macros
    -0.07
     nÄĽho
    -0.07
    POSITIVE LOGITS
     lower
    0.09
     earlier
    0.08
     original
    0.07
     Lower
    0.07
     district
    0.07
    lower
    0.07
     below
    0.06
     previous
    0.06
     Below
    0.06
    NotFoundError
    0.06
    Activations Density 0.018%

    No Known Activations