© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 82452
    Prev
    Next
    INDEX
    Explanations

    mentions of transitions or movements between states, whether physical, social, or conceptual

    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
     alternatively
    -0.07
    101
    -0.06
    ilit
    -0.06
    ione
    -0.06
    anan
    -0.06
    kh
    -0.06
    iers
    -0.06
    esk
    -0.06
    altern
    -0.06
    oun
    -0.06
    POSITIVE LOGITS
    /jav
    0.07
     onto
    0.07
    RTOS
    0.07
    ORA
    0.07
    åĪ°äºĨ
    0.07
     into
    0.07
    acobian
    0.07
    onto
    0.07
     cả
    0.07
     other
    0.07
    Activations Density 0.024%

    No Known Activations