© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84510
    Prev
    Next
    INDEX
    Explanations

    references to seasonal activities and holiday-themed events

    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
     (!((
    -0.07
    åıĬãģ³
    -0.07
     persons
    -0.07
    ανά
    -0.07
    çĦ¡ãģĹ
    -0.07
    íķĺìŬ
    -0.06
    persons
    -0.06
    çĬ
    -0.06
    cae
    -0.06
     ÙĪÛĮÚ©ÛĮ
    -0.06
    POSITIVE LOGITS
     âŁ
    0.08
     --
    0.08
     —
    0.08
     probs
    0.07
    iiii
    0.07
     >>
    0.07
     "'
    0.06
    'd
    0.06
     "[
    0.06
    oriously
    0.06
    Activations Density 1.820%

    No Known Activations