© 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. 60818
    Prev
    Next
    INDEX
    Explanations

    phrases indicating accountability or lack thereof in various contexts

    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
    emale
    -0.07
     miscon
    -0.06
    avin
    -0.06
    elda
    -0.06
    proper
    -0.06
    Ļ
    -0.06
     sharedInstance
    -0.06
    Ø£Ùħ
    -0.06
    hei
    -0.06
    ilion
    -0.06
    POSITIVE LOGITS
     whit
    0.07
    irsch
    0.07
    kish
    0.07
    iar
    0.06
    aru
    0.06
     ActionTypes
    0.06
     true
    0.06
    839
    0.06
    anter
    0.06
     credibility
    0.06
    Activations Density 0.038%

    No Known Activations