© 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. 15-LLAMASCOPE-RES-131K
    11. 89333
    Prev
    Next
    INDEX
    Explanations

    phrases indicating restrictions, limitations, or conditions

    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
    ys
    -0.06
    ξι
    -0.06
    ativ
    -0.06
    RAINT
    -0.06
    angen
    -0.06
     subt
    -0.05
     procurement
    -0.05
    emi
    -0.05
     wellness
    -0.05
    ovÃŃ
    -0.05
    POSITIVE LOGITS
    raq
    0.07
    uffle
    0.07
    orts
    0.07
     viewType
    0.07
     accident
    0.06
    ceb
    0.06
    PROFILE
    0.06
    ixo
    0.06
     Accident
    0.06
    -Requested
    0.06
    Activations Density 0.001%

    No Known Activations