© 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. 84046
    Prev
    Next
    INDEX
    Explanations

    specific nouns related to items, products, or environmental concerns

    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
     pÅĻip
    -0.07
    bris
    -0.07
     nowrap
    -0.06
    urious
    -0.06
    اÙģ
    -0.06
     дела
    -0.06
    ặc
    -0.06
    äºĭæĥħ
    -0.06
    à¹īà¸Ńà¸Ļ
    -0.06
     quỹ
    -0.06
    POSITIVE LOGITS
     replace
    0.12
     replaced
    0.11
     Replace
    0.10
    replace
    0.10
    Replace
    0.10
     replacement
    0.10
     replacing
    0.09
     REPLACE
    0.09
     altogether
    0.09
    _replace
    0.09
    Activations Density 0.038%

    No Known Activations