© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16094
    Prev
    Next
    INDEX
    Explanations

    relationships and associations involving collaborative efforts and roles within various organizations

    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
    ìĬĪ
    -0.10
    ataka
    -0.08
    Ŀ
    -0.08
    jsc
    -0.08
     ÙĪرÙĪد
    -0.07
    @brief
    -0.07
     VÅ¡ech
    -0.07
     henüz
    -0.07
    OwnProperty
    -0.07
     yoksa
    -0.07
    POSITIVE LOGITS
     several
    0.23
     various
    0.21
     numerous
    0.16
     Several
    0.15
     many
    0.14
    Several
    0.14
     Various
    0.14
     both
    0.14
     varios
    0.12
     plusieurs
    0.12
    Activations Density 0.064%

    No Known Activations