© 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. 86924
    Prev
    Next
    INDEX
    Explanations

    conjunctions and linking phrases in the text

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

    Coordinating conjunctions "and" and "or" used to connect related concepts in informational or commercial content, often linking main features with supplementary elements.

    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
    ipher
    -0.07
    olik
    -0.07
    -0.07
    ÏĦιÏĥ
    -0.06
    esini
    -0.06
     zwar
    -0.06
    itori
    -0.06
    burgh
    -0.06
     Din
    -0.06
     Kear
    -0.06
    POSITIVE LOGITS
    MBED
    0.07
    merc
    0.06
    BaseContext
    0.06
    scriber
    0.06
    erosis
    0.06
    .Feature
    0.06
    CAA
    0.06
    าร
    0.06
    uzzer
    0.06
     ev
    0.06
    Activations Density 0.079%

    No Known Activations