© 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. 40807
    Prev
    Next
    INDEX
    Explanations

    phrases related to nurturing and caregiving roles

    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
    adin
    -0.08
    аж
    -0.08
    _MSB
    -0.07
    VIC
    -0.07
    ORMAT
    -0.07
    λοÏħ
    -0.07
     baj
    -0.07
    ìļ´ëį°
    -0.07
    éĴ®
    -0.07
    Separated
    -0.07
    POSITIVE LOGITS
    fuck
    0.06
     Fuck
    0.06
     rare
    0.06
     fuck
    0.05
     -
    0.05
     yearly
    0.05
     security
    0.05
     Kov
    0.05
     within
    0.05
     Rare
    0.05
    Activations Density 0.000%

    No Known Activations