© 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. 9-LLAMASCOPE-RES-131K
    11. 96876
    Prev
    Next
    INDEX
    Explanations

    terms related to food and poverty assistance

    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
    onet
    -0.07
    ande
    -0.06
    roe
    -0.06
    arde
    -0.06
    orman
    -0.06
    ally
    -0.06
    lou
    -0.06
    anke
    -0.06
    oe
    -0.06
     grind
    -0.06
    POSITIVE LOGITS
    sumer
    0.07
    zcze
    0.07
    #
    0.07
    ujemy
    0.07
    parity
    0.07
    _Tis
    0.07
    -REAL
    0.06
    ırak
    0.06
    acier
    0.06
    orama
    0.06
    Activations Density 0.001%

    No Known Activations