© 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. 16711
    Prev
    Next
    INDEX
    Explanations

    instances of power dynamics and compliance in interactions

    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
    ighth
    -0.07
    OfClass
    -0.07
    ahan
    -0.06
    ì¹´ëĿ¼
    -0.06
    аÑĢÑĩ
    -0.06
    ETYPE
    -0.06
    terra
    -0.06
    ittest
    -0.06
    ãĥ©ãĤ¹
    -0.06
    clamation
    -0.06
    POSITIVE LOGITS
     kabul
    0.09
     accept
    0.09
     tempor
    0.09
     ACCEPT
    0.09
     acceptance
    0.08
     accepts
    0.08
     agree
    0.08
     Accept
    0.08
    _accept
    0.08
     accepted
    0.08
    Activations Density 0.027%

    No Known Activations