© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2953
    Prev
    Next
    INDEX
    Explanations

    phrases that include parenthetical remarks or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Opening parenthesis that begins an aside, often containing a joke, pun, clarification, or additional commentary that interrupts the main text flow with a casual or conversational tone.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    nat
    -0.06
    ancel
    -0.06
    alc
    -0.06
    æıı
    -0.06
    ng
    -0.06
     Boyle
    -0.06
     èı
    -0.06
    _factory
    -0.06
     Pow
    -0.06
     Burgess
    -0.06
    POSITIVE LOGITS
     literal
    0.32
     literally
    0.31
     Liter
    0.28
    liter
    0.28
    literal
    0.24
     pun
    0.24
    Liter
    0.24
     Literal
    0.23
    pun
    0.23
     figur
    0.21
    Activations Density 0.145%

    No Known Activations