© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87015
    Prev
    Next
    INDEX
    Explanations

    terms related to server and system configurations

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

    Tokens that describe computer systems, particularly networked components or software elements that are added, connected, or configured dynamically within technology infrastructure.

    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
    .scalablytyped
    -0.09
    IRT
    -0.08
    OffsetTable
    -0.08
    fsp
    -0.07
    /GPL
    -0.07
    icari
    -0.07
    iedad
    -0.07
    IMIT
    -0.07
     damer
    -0.07
    usz
    -0.07
    POSITIVE LOGITS
     Phen
    0.06
    chk
    0.06
     Orchard
    0.06
    arro
    0.05
     Matters
    0.05
    imuth
    0.05
    Enumeration
    0.05
     Lon
    0.05
     Express
    0.05
     OS
    0.05
    Activations Density 0.040%

    No Known Activations