© 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. 57954
    Prev
    Next
    INDEX
    Explanations

    suggestions and recommendations related to home inspections and maintenance

    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
    yang
    -0.07
    ¯¯
    -0.07
    qa
    -0.07
    InBackground
    -0.07
     mainScreen
    -0.07
    ãģħ
    -0.07
    auled
    -0.06
    åijĺ
    -0.06
    ÑĥзÑĭ
    -0.06
     hum
    -0.06
    POSITIVE LOGITS
     best
    0.10
    best
    0.09
    æľĢä½³
    0.08
     appropri
    0.07
     optimal
    0.07
    arch
    0.07
     options
    0.07
     optimum
    0.07
     architectural
    0.07
     alternative
    0.06
    Activations Density 0.028%

    No Known Activations