© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 41090
    Prev
    Next
    INDEX
    Explanations

    references to government regulations and legal frameworks

    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
    ior
    -0.06
    aint
    -0.06
    864
    -0.06
    anks
    -0.06
    .ResumeLayout
    -0.06
    etto
    -0.06
     Hoffman
    -0.06
    ãĥĥ
    -0.05
    uito
    -0.05
    .newBuilder
    -0.05
    POSITIVE LOGITS
    /Dk
    0.10
     caracteres
    0.07
    tent
    0.07
    æ®
    0.07
    urum
    0.07
    Ñģов
    0.07
    менÑĪ
    0.07
     -*-č↵
    0.07
    osu
    0.07
     Merkez
    0.06
    Activations Density 0.286%

    No Known Activations