© 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. 70854
    Prev
    Next
    INDEX
    Explanations

    references to resolutions and decisions made by a governing body

    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
    ANGER
    -0.07
    /AFP
    -0.07
    .internet
    -0.06
    urge
    -0.06
    uger
    -0.06
    anger
    -0.06
    ickerView
    -0.06
    責
    -0.06
    InstanceState
    -0.06
    rompt
    -0.06
    POSITIVE LOGITS
     ninth
    0.07
    9
    0.07
    iba
    0.07
    ingroup
    0.07
     Hod
    0.06
     ä¸
    0.06
    ulu
    0.06
     reserve
    0.06
    arel
    0.06
    escal
    0.06
    Activations Density 0.029%

    No Known Activations