© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106378
    Prev
    Next
    INDEX
    Explanations

    issues related to conflict and violence, particularly in a historical or societal context

    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
     cant
    -0.07
    毫
    -0.06
     Downs
    -0.06
     Canton
    -0.06
     Myst
    -0.05
    arf
    -0.05
     mistr
    -0.05
     completely
    -0.05
    å¦Ĥ
    -0.05
     '{
    -0.05
    POSITIVE LOGITS
     relatively
    0.09
     manageable
    0.09
     merely
    0.09
     zatÃŃm
    0.08
    ãģ¾ãģł
    0.08
     spared
    0.08
     worst
    0.08
    å°ļ
    0.07
    лаж
    0.07
     relativ
    0.07
    Activations Density 0.050%

    No Known Activations