© 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. 75372
    Prev
    Next
    INDEX
    Explanations

    the word "this" in various contexts, indicating a focus on specific references or ideas being discussed

    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
    еÑĢÑĪ
    -0.08
    ÑģÑİ
    -0.07
    ÑĢаÑĤи
    -0.07
    _ASCII
    -0.07
    ÑĢик
    -0.07
    лава
    -0.07
    starter
    -0.07
    женÑĮ
    -0.06
    омен
    -0.06
    à¹Ħà¸Ł
    -0.06
    POSITIVE LOGITS
    :
    0.13
     _:
    0.07
     :
    0.07
    angkan
    0.07
    _:
    0.07
    ा:
    0.06
    bang
    0.06
    mares
    0.06
    olio
    0.06
    /how
    0.06
    Activations Density 0.004%

    No Known Activations