© 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. 84540
    Prev
    Next
    INDEX
    Explanations

    instances of time-related actions and delays

    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
    ÏĢά
    -0.07
    tent
    -0.07
    lasses
    -0.06
    days
    -0.06
    defgroup
    -0.06
    dust
    -0.06
    ман
    -0.06
    roma
    -0.06
    week
    -0.06
    iped
    -0.06
    POSITIVE LOGITS
     пÑĢибÑĭ
    0.08
     arrival
    0.07
     hur
    0.07
     bree
    0.07
     late
    0.07
     personals
    0.07
    //{{
    0.06
    æµģéĩı
    0.06
     ëĬ
    0.06
     arrive
    0.06
    Activations Density 0.015%

    No Known Activations