© 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. 77605
    Prev
    Next
    INDEX
    Explanations

    code elements related to programming constructs and patterns

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

    Programming code elements or variable names that are being discussed or modified in software development contexts.

    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
    leans
    -0.07
     Frid
    -0.07
    διά
    -0.07
    atı
    -0.07
    наÑĢод
    -0.07
    .reloadData
    -0.07
     Separator
    -0.07
    opia
    -0.06
    Ïħ
    -0.06
    onica
    -0.06
    POSITIVE LOGITS
     ::=
    0.09
     =
    0.09
    ColorBrush
    0.06
     def
    0.06
    =#
    0.06
    EFAULT
    0.06
    etheless
    0.06
    cee
    0.06
    =""↵
    0.06
    mlin
    0.05
    Activations Density 0.305%

    No Known Activations