© 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. 70949
    Prev
    Next
    INDEX
    Explanations

    phrases indicating disputes or conflicts involving accusations and political implications

    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
    zac
    -0.06
     dumb
    -0.06
     reportedly
    -0.05
     scour
    -0.05
    reb
    -0.05
     DEFINE
    -0.05
    .um
    -0.05
     DIY
    -0.05
    roc
    -0.05
     structures
    -0.05
    POSITIVE LOGITS
     nhằm
    0.09
    èĵ
    0.08
     attempt
    0.08
    缮çļĦ
    0.08
    HEME
    0.08
    intent
    0.08
    kker
    0.07
    Intent
    0.07
     intent
    0.07
     purpose
    0.07
    Activations Density 0.039%

    No Known Activations