© 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. 105648
    Prev
    Next
    INDEX
    Explanations

    references to humanitarian organizations and relief efforts

    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
    ibs
    -0.07
    ddit
    -0.07
    abase
    -0.07
    enan
    -0.07
    sterol
    -0.07
    .Atomic
    -0.07
    mant
    -0.06
    ceipt
    -0.06
    èIJ½
    -0.06
    ìłĪ
    -0.06
    POSITIVE LOGITS
     Geneva
    0.09
    enberg
    0.08
     humanitarian
    0.07
     relief
    0.07
     char
    0.07
     neutrality
    0.06
    енÑĤÑĥ
    0.06
    Gene
    0.06
     quil
    0.06
    illard
    0.06
    Activations Density 0.019%

    No Known Activations