© 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. 5-LLAMASCOPE-RES-131K
    11. 125946
    Prev
    Next
    INDEX
    Explanations

    terms related to linguistic or philosophical concepts

    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
    ré
    -0.07
     Shen
    -0.06
    ipples
    -0.06
    Pooling
    -0.06
    اذ
    -0.06
     bout
    -0.06
    ipple
    -0.06
    ecz
    -0.06
    bj
    -0.06
    uzzi
    -0.06
    POSITIVE LOGITS
    eras
    0.08
    urette
    0.07
    agle
    0.07
    ants
    0.06
    WARE
    0.06
    angelo
    0.06
    .deb
    0.06
    arel
    0.06
    gpu
    0.06
     اÙĦÙĤر
    0.06
    Activations Density 0.001%

    No Known Activations