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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75005
    Prev
    Next
    INDEX
    Explanations

    technical commands and programming-related terms in the context of scripting

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

    References to command line interfaces, shell environments, or terminal commands, often in the context of tutorial instructions or technical documentation.

    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
     Ger
    -0.06
    eck
    -0.06
    he
    -0.06
    ISA
    -0.06
     res
    -0.06
     fla
    -0.05
     complement
    -0.05
    yna
    -0.05
     bullet
    -0.05
     Village
    -0.05
    POSITIVE LOGITS
     terminal
    0.13
     prompt
    0.12
     Terminal
    0.12
    terminal
    0.12
    _prompt
    0.11
     terminals
    0.11
    Terminal
    0.11
    -terminal
    0.11
    prompt
    0.10
     shell
    0.10
    Activations Density 0.069%

    No Known Activations