© 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. 76970
    Prev
    Next
    INDEX
    Explanations

    the word "By" as a marker for authorship or attribution in text

    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
    ouch
    -0.08
    endo
    -0.08
    otal
    -0.07
    ritis
    -0.07
     Scha
    -0.07
    atis
    -0.07
    ilter
    -0.07
    atra
    -0.06
    leck
    -0.06
    _firestore
    -0.06
    POSITIVE LOGITS
     Gamb
    0.07
    erdem
    0.07
     serialVersionUID
    0.07
    еви
    0.06
    'gc
    0.06
    ERCHANT
    0.06
    lish
    0.06
    _SUPPORTED
    0.06
    Merchant
    0.06
     Merchant
    0.06
    Activations Density 0.006%

    No Known Activations