© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71571
    Prev
    Next
    INDEX
    Explanations

    references to AI capabilities and limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Descriptions of AI systems' capabilities or limitations, often in comparison to human abilities or biological processes.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    hue
    -0.07
    ãĥ¡ãĥ©
    -0.07
    antt
    -0.07
    .Align
    -0.07
     æĭĽ
    -0.07
    AMPL
    -0.06
    omencl
    -0.06
    ernes
    -0.06
    ottes
    -0.06
     à¤īप
    -0.06
    POSITIVE LOGITS
     humans
    0.08
     Humans
    0.08
     human
    0.07
    Humans
    0.07
     natural
    0.07
     complex
    0.07
     convers
    0.06
     Human
    0.06
     understands
    0.06
     Mono
    0.06
    Activations Density 0.014%

    No Known Activations