© 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. 78265
    Prev
    Next
    INDEX
    Explanations

    phrases indicating social status or class distinctions

    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
    AndGet
    -0.08
    _ABI
    -0.07
    orca
    -0.07
    bara
    -0.07
    ãĤĤãģĨ
    -0.07
    Äı
    -0.07
     Tep
    -0.07
    ucus
    -0.07
    arat
    -0.07
     Tay
    -0.06
    POSITIVE LOGITS
     alike
    0.07
     most
    0.07
     preference
    0.06
     earliest
    0.06
    etc
    0.05
    most
    0.05
    emy
    0.05
     Moz
    0.05
    934
    0.05
     cha
    0.05
    Activations Density 0.024%

    No Known Activations