© 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 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. 71220
    Prev
    Next
    INDEX
    Explanations

    specific terms related to product categories and brands in various contexts

    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
    Ùĩ
    -0.13
    न
    -0.10
    ska
    -0.10
    siz
    -0.08
    udit
    -0.08
    scheduler
    -0.07
    slope
    -0.07
    sar
    -0.07
    Ñĩина
    -0.06
    scape
    -0.06
    POSITIVE LOGITS
    sWith
    0.24
    们
    0.20
    swith
    0.20
    Ñķ
    0.20
    sthrough
    0.19
    (s
    0.19
    ss
    0.19
    [s
    0.18
    sto
    0.18
    à¥įस
    0.18
    Activations Density 0.168%

    No Known Activations