© 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. 40268
    Prev
    Next
    INDEX
    Explanations

    instances of self-reflection and questioning of social issues

    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
     Tough
    -0.06
     Stake
    -0.06
     Grat
    -0.06
    Hang
    -0.06
    XXXX
    -0.06
     Sch
    -0.06
     Fukushima
    -0.06
     Ein
    -0.05
     Barn
    -0.05
    sto
    -0.05
    POSITIVE LOGITS
    olon
    0.08
    efon
    0.08
    çŃ
    0.08
     PACKET
    0.07
     intersection
    0.07
     trop
    0.07
     Intersection
    0.07
    ubat
    0.07
     dismantle
    0.07
     å¨
    0.07
    Activations Density 0.002%

    No Known Activations