© 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. 15-LLAMASCOPE-RES-131K
    11. 852
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking actions or engaging in activities

    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
    .
    -0.06
    yte
    -0.06
    ears
    -0.06
     Cunningham
    -0.06
    pend
    -0.06
    ,
    -0.06
    ิà¹ī
    -0.06
     bush
    -0.06
    outil
    -0.06
     Champ
    -0.06
    POSITIVE LOGITS
    ñana
    0.08
    UTILITY
    0.07
     Král
    0.07
    Ware
    0.07
     ÙĨظر
    0.07
    _iface
    0.07
    /***/
    0.07
    ktion
    0.07
    VENTORY
    0.07
    rippling
    0.07
    Activations Density 0.043%

    No Known Activations