© 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. 104042
    Prev
    Next
    INDEX
    Explanations

    phrases indicating returning or coming back

    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
    åĢŁ
    -0.07
    este
    -0.07
    ahkan
    -0.06
     vent
    -0.06
    oyal
    -0.06
     Bye
    -0.06
    \\/
    -0.06
    ono
    -0.06
     DLC
    -0.06
     kıs
    -0.06
    POSITIVE LOGITS
     home
    0.09
     hometown
    0.07
     thuis
    0.06
     huis
    0.06
    home
    0.06
    HOME
    0.06
    Home
    0.06
     retorno
    0.06
    à¸Īาà¸ģà¸ģาร
    0.06
     alive
    0.06
    Activations Density 0.011%

    No Known Activations