© 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. 27518
    Prev
    Next
    INDEX
    Explanations

    terminology related to privatization and economic policies

    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
    resa
    -0.07
    dur
    -0.07
     Dur
    -0.06
    gel
    -0.06
    agara
    -0.06
    uben
    -0.06
    obel
    -0.06
    ersiz
    -0.06
    cido
    -0.06
    .scalablytyped
    -0.06
    POSITIVE LOGITS
     proceeds
    0.08
     Proceed
    0.07
     hấp
    0.07
     proceedings
    0.07
     proceed
    0.07
    SETS
    0.06
    ceed
    0.06
    ilig
    0.06
    orio
    0.06
    362
    0.06
    Activations Density 0.003%

    No Known Activations