© 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. 129265
    Prev
    Next
    INDEX
    Explanations

    social media posts that contain various types of media mentions, such as photos and videos

    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
    -0.06
    las
    -0.06
    ollo
    -0.06
     --
    -0.06
     Hancock
    -0.06
    ancock
    -0.06
    1
    -0.06
    0
    -0.06
    824
    -0.05
    lag
    -0.05
    POSITIVE LOGITS
     migrationBuilder
    0.08
     Bench
    0.08
    OffsetTable
    0.07
    ¶ģ
    0.07
     '{@
    0.07
    udiant
    0.07
    CEE
    0.07
    .GetById
    0.07
    CSR
    0.07
    CDF
    0.07
    Activations Density 0.001%

    No Known Activations