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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78269
    Prev
    Next
    INDEX
    Explanations

    themes related to the inherent value and dignity of human life

    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
    оÑı
    -0.07
    hof
    -0.07
    andest
    -0.07
    odia
    -0.06
    plit
    -0.06
    زد
    -0.06
    roph
    -0.06
    ogs
    -0.06
    oug
    -0.06
    ovol
    -0.06
    POSITIVE LOGITS
     worth
    0.08
     warrant
    0.07
     God
    0.07
    aver
    0.07
     human
    0.07
     unique
    0.06
     affected
    0.06
     created
    0.06
    God
    0.06
     dignity
    0.06
    Activations Density 0.018%

    No Known Activations