© 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. 76251
    Prev
    Next
    INDEX
    Explanations

    events or actions related to pause, stop, or a temporary halt

    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
    ieder
    -0.07
    athers
    -0.07
    disposed
    -0.07
     dismiss
    -0.07
    iggins
    -0.06
    _INCLUDED
    -0.06
    ä¾
    -0.06
    dismiss
    -0.06
    ÅĻes
    -0.06
    dispose
    -0.06
    POSITIVE LOGITS
     suspend
    0.17
     susp
    0.16
     stop
    0.15
     suspension
    0.15
     halt
    0.15
     suspended
    0.14
    suspend
    0.14
    åģľæŃ¢
    0.14
     stopped
    0.13
     pause
    0.13
    Activations Density 0.145%

    No Known Activations