© 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. 72172
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and evidence

    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
    ixel
    -0.07
    ena
    -0.07
    appable
    -0.07
    éĤ¦
    -0.06
    ckill
    -0.06
    коз
    -0.06
     arbit
    -0.06
    .getSharedPreferences
    -0.06
    anka
    -0.06
    anguages
    -0.06
    POSITIVE LOGITS
     hears
    0.09
    rette
    0.07
     relevance
    0.07
    YTE
    0.07
    &&!
    0.06
    addock
    0.06
    aset
    0.06
     prejudice
    0.06
     sidebar
    0.06
    è¨Ĭ
    0.06
    Activations Density 0.022%

    No Known Activations