© 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. 84117
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and planning

    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
    amp
    -0.08
    raquo
    -0.08
    rost
    -0.07
    stry
    -0.07
    ired
    -0.06
    éf
    -0.06
    Ñĩин
    -0.06
    pon
    -0.06
    inem
    -0.06
     зам
    -0.06
    POSITIVE LOGITS
    EDA
    0.06
    IJľ
    0.06
    enance
    0.06
    typeid
    0.06
    iets
    0.06
    neck
    0.06
     á
    0.06
    een
    0.06
    thing
    0.06
    suspend
    0.06
    Activations Density 0.242%

    No Known Activations