© 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. 61555
    Prev
    Next
    INDEX
    Explanations

    themes related to peace and social justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text segments containing or adjacent to the word "peace" in various contexts, often discussing concepts of harmony, resolution of conflict, or peaceful relations between nations, groups, or individuals.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ntag
    -0.07
    otel
    -0.07
    .RunWith
    -0.06
    ubyte
    -0.06
    RITE
    -0.06
    дина
    -0.06
    nez
    -0.06
    amber
    -0.06
     lif
    -0.06
    ½
    -0.06
    POSITIVE LOGITS
     peace
    0.15
     Peace
    0.14
    peace
    0.13
    Peace
    0.13
     tranqu
    0.09
     peaceful
    0.09
    pac
    0.07
     disarm
    0.07
     Pac
    0.07
    /rest
    0.07
    Activations Density 0.025%

    No Known Activations