© 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. 126885
    Prev
    Next
    INDEX
    Explanations

    instances of significant personal experiences

    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
    ilon
    -0.08
    clc
    -0.06
     Inn
    -0.06
    hti
    -0.06
    pron
    -0.06
     public
    -0.06
     among
    -0.06
     surrounding
    -0.06
     le
    -0.05
    infeld
    -0.05
    POSITIVE LOGITS
     Household
    0.08
     household
    0.08
     bedroom
    0.08
     kitchen
    0.08
     Bedroom
    0.07
    ichen
    0.07
    _TV
    0.07
     кÑĥÑħ
    0.07
     Kitchen
    0.07
     TV
    0.07
    Activations Density 0.044%

    No Known Activations