© 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. 57820
    Prev
    Next
    INDEX
    Explanations

    themes of maternal appreciation and celebration

    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
    aland
    -0.07
     Furious
    -0.07
    ï¼ł
    -0.06
    ãģıãĤĵ
    -0.06
    sei
    -0.06
    leans
    -0.06
     MessageBoxIcon
    -0.06
    ersist
    -0.06
    apur
    -0.06
    itus
    -0.06
    POSITIVE LOGITS
     lips
    0.06
    .enter
    0.06
     compens
    0.06
    oret
    0.06
     dim
    0.06
    kins
    0.06
    _plus
    0.06
    lint
    0.06
     pall
    0.06
     alike
    0.06
    Activations Density 0.000%

    No Known Activations