© 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. 71383
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the start or initiation of a new activity or project

    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
    irie
    -0.07
    FormatException
    -0.07
    eel
    -0.07
    zw
    -0.07
    notated
    -0.07
    eless
    -0.07
    åIJ¾
    -0.06
    vit
    -0.06
    беÑĢ
    -0.06
    å¾ħ
    -0.06
    POSITIVE LOGITS
     journey
    0.08
     mission
    0.07
     task
    0.07
     tasks
    0.07
    837
    0.07
     careers
    0.06
    -task
    0.06
     career
    0.06
     adventure
    0.06
     quest
    0.06
    Activations Density 0.005%

    No Known Activations