© 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. 22-LLAMASCOPE-RES-131K
    11. 4260
    Prev
    Next
    INDEX
    Explanations

    phrases related to group accommodations and social gatherings

    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
    ounge
    -0.08
    iminal
    -0.07
    itra
    -0.07
    øre
    -0.07
     descendant
    -0.07
    اÙĥÙĨ
    -0.07
    ouncy
    -0.07
     Dün
    -0.07
    rschein
    -0.07
    ounce
    -0.06
    POSITIVE LOGITS
     families
    0.11
     business
    0.10
     groups
    0.10
     couples
    0.09
     family
    0.09
     Families
    0.09
     corporate
    0.09
    groups
    0.08
     Corporate
    0.08
     extended
    0.08
    Activations Density 0.023%

    No Known Activations