© 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. 93689
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditional or simultaneous actions

    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
    oleon
    -0.08
    .nlm
    -0.08
    lavÃŃ
    -0.08
     zwar
    -0.08
    ignKey
    -0.08
    DataTask
    -0.08
    ↵↵
    -0.08
    .slim
    -0.07
    eselect
    -0.07
    -UA
    -0.07
    POSITIVE LOGITS
     also
    0.11
     being
    0.10
    s
    0.10
     Also
    0.09
    Also
    0.08
     ALSO
    0.07
    also
    0.07
     still
    0.07
     simultaneously
    0.07
    ëıĦ
    0.07
    Activations Density 0.016%

    No Known Activations