© 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. 85275
    Prev
    Next
    INDEX
    Explanations

    descriptions of richness and depth in various contexts, particularly relating to community, culture, and history

    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
    isco
    -0.07
    404
    -0.07
    zon
    -0.06
     minimum
    -0.06
    abolic
    -0.06
    ivic
    -0.06
    ئ
    -0.06
    gle
    -0.06
    403
    -0.06
     LÆ°u
    -0.06
    POSITIVE LOGITS
     rich
    0.12
     richer
    0.11
    rich
    0.11
    ened
    0.10
     richest
    0.10
    -rich
    0.10
    ly
    0.09
    uckle
    0.09
     richness
    0.08
     tape
    0.08
    Activations Density 0.018%

    No Known Activations