© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 57468
    Prev
    Next
    INDEX
    Explanations

    references to United Nations activities and resolutions

    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
     Hem
    -0.06
     Green
    -0.06
    uli
    -0.06
     hem
    -0.06
     hap
    -0.05
     hang
    -0.05
     Coach
    -0.05
    quil
    -0.05
    ánt
    -0.05
    ulia
    -0.05
    POSITIVE LOGITS
     sanctions
    0.08
     UNS
    0.08
    UN
    0.08
     Security
    0.08
    rix
    0.08
    untime
    0.08
    peace
    0.07
     peace
    0.07
    lamaz
    0.07
    Security
    0.07
    Activations Density 0.005%

    No Known Activations