© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83530
    Prev
    Next
    INDEX
    Explanations

    phrases related to interactions and relationships with others

    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
    LOB
    -0.06
     Hole
    -0.06
    croft
    -0.06
    insula
    -0.06
    avl
    -0.06
     dev
    -0.06
    IFIC
    -0.06
    ÙĪØ±ÛĮ
    -0.06
    thon
    -0.06
    dev
    -0.06
    POSITIVE LOGITS
     encounter
    0.15
     encounters
    0.15
     encountered
    0.12
     Encounter
    0.12
     encount
    0.12
     encountering
    0.12
     rencontre
    0.11
     chances
    0.11
    éģĩ
    0.11
    enc
    0.10
    Activations Density 0.071%

    No Known Activations