© 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. 9-LLAMASCOPE-RES-131K
    11. 95200
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving in or yielding to pressure or external demands

    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
    illion
    -0.08
    ãĥ¼ãĥķ
    -0.07
    loub
    -0.07
    hsi
    -0.07
    ollen
    -0.06
    ableObject
    -0.06
    YTE
    -0.06
    idges
    -0.06
    ewater
    -0.06
    è£Ĥ
    -0.06
    POSITIVE LOGITS
    ukkan
    0.07
    209
    0.07
    .lv
    0.06
    isex
    0.06
    ISC
    0.06
     Sherlock
    0.06
    471
    0.06
     Åŀehir
    0.06
     atmospheric
    0.06
    eral
    0.06
    Activations Density 0.012%

    No Known Activations