© 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. 29047
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and indictments

    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
    ysz
    -0.06
    aan
    -0.06
    CLA
    -0.05
    691
    -0.05
    ced
    -0.05
    _POINTS
    -0.05
    ÑĪиб
    -0.05
    comments
    -0.05
    _disc
    -0.05
    POINTS
    -0.05
    POSITIVE LOGITS
     indict
    0.08
    reesome
    0.08
    lator
    0.08
    uze
    0.08
     indictment
    0.07
    igon
    0.07
    orus
    0.07
    Anonymous
    0.07
    iens
    0.07
    ãĥ³ãĥIJãĥ¼
    0.07
    Activations Density 0.003%

    No Known Activations