© 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. 56870
    Prev
    Next
    INDEX
    Explanations

    specific video compression formats and related technologies

    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
    rup
    -0.07
    erto
    -0.07
    insk
    -0.06
    FTA
    -0.06
    abee
    -0.06
    sep
    -0.06
    mie
    -0.06
    deep
    -0.06
    arp
    -0.06
    imm
    -0.06
    POSITIVE LOGITS
    å¼ı
    0.08
    ãĤĬãģ«
    0.08
    tember
    0.07
    çī
    0.07
    /javascript
    0.07
    μη
    0.07
    Subviews
    0.07
    ted
    0.07
    Å©
    0.07
    анÑģи
    0.07
    Activations Density 0.001%

    No Known Activations