© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 105653
    Prev
    Next
    INDEX
    Explanations

    phrases related to a consistent or regular occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ish
    -0.09
    ase
    -0.09
    sdale
    -0.08
    berg
    -0.07
    \Php
    -0.07
    esi
    -0.07
     Maze
    -0.07
    outs
    -0.06
    KERNEL
    -0.06
    rez
    -0.06
    POSITIVE LOGITS
    .gdx
    0.08
    dır
    0.08
    enger
    0.08
    elor
    0.07
    nement
    0.07
    ymmetric
    0.07
    plate
    0.06
    icari
    0.06
     Isles
    0.06
    istent
    0.06
    Activations Density 0.009%

    No Known Activations