© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 82283
    Prev
    Next
    INDEX
    Explanations

    terms related to accusations and legal charges

    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
    dden
    -0.08
    thon
    -0.06
    utz
    -0.06
    ãĥ³ãĥĢ
    -0.06
    asant
    -0.06
    ora
    -0.06
    åĵį
    -0.06
     иÑģк
    -0.06
     éļ
    -0.06
    éŁ¿
    -0.06
    POSITIVE LOGITS
    aru
    0.07
    edly
    0.07
    pNet
    0.06
    endale
    0.06
     ly
    0.06
    .scalablytyped
    0.06
    ipher
    0.06
    ATUS
    0.06
    /lic
    0.06
    wig
    0.06
    Activations Density 0.004%

    No Known Activations