© 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. 15-LLAMASCOPE-RES-131K
    6. 103429
    Prev
    Next
    INDEX
    Explanations

    syntax elements related to programming and code structure

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

    Closing syntax elements at the end of code blocks, typically right before explanatory text or the next code segment begins.

    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
    ingers
    -0.06
    egis
    -0.06
    ag
    -0.06
    acho
    -0.06
     emp
    -0.06
    prox
    -0.06
     Edwin
    -0.06
     protocol
    -0.05
    ippo
    -0.05
     prox
    -0.05
    POSITIVE LOGITS
     dabei
    0.07
    AFX
    0.07
    abei
    0.07
    apel
    0.07
     compartment
    0.07
    OUCH
    0.07
    resi
    0.07
    lsi
    0.07
     (*((
    0.07
    GroupBox
    0.07
    Activations Density 0.009%

    No Known Activations