© 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. 22-LLAMASCOPE-RES-131K
    11. 3992
    Prev
    Next
    INDEX
    Explanations

    phrases expressing excessive or problematic quantities

    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
     лиÑĪ
    -0.08
    oru
    -0.07
     Scout
    -0.07
    νο
    -0.07
    lc
    -0.07
    oppable
    -0.07
     scout
    -0.06
    è¡
    -0.06
    ÙĪغ
    -0.06
     PARTICULAR
    -0.06
    POSITIVE LOGITS
     often
    0.15
    often
    0.13
     Often
    0.10
     frequently
    0.10
     souvent
    0.10
     many
    0.10
    Often
    0.09
     Äįasto
    0.08
     oft
    0.08
    requently
    0.08
    Activations Density 0.006%

    No Known Activations