© 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. 72447
    Prev
    Next
    INDEX
    Explanations

    references and discussions related to law enforcement

    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
    åĽ
    -0.07
    onse
    -0.07
    å°ĸ
    -0.07
    rias
    -0.07
    ational
    -0.07
    Traits
    -0.06
    uegos
    -0.06
    RACT
    -0.06
    AGE
    -0.06
     láºŃp
    -0.06
    POSITIVE LOGITS
    rence
    0.13
    fully
    0.11
    yer
    0.10
     enforcement
    0.10
    erence
    0.09
    fulness
    0.09
    renc
    0.08
    ngth
    0.07
    lessness
    0.07
    yers
    0.07
    Activations Density 0.021%

    No Known Activations