© 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. 77954
    Prev
    Next
    INDEX
    Explanations

    unique identifiers or numbers related to various entities

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

    Online usernames or handles that identify individual posters in forum discussions, comment sections, or social media platforms.

    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
    cial
    -0.08
     Haskell
    -0.08
    ãĥģãĥ¥
    -0.07
     ØŃاÙĦ
    -0.07
    ONO
    -0.07
    .serializer
    -0.07
    åľŃ
    -0.07
    имв
    -0.07
    SOR
    -0.07
    جÙĬ
    -0.07
    POSITIVE LOGITS
    istrovstvÃŃ
    0.06
    iden
    0.06
     Forum
    0.06
    SPAN
    0.06
    123
    0.06
    affles
    0.05
    αι
    0.05
    /Edit
    0.05
    629
    0.05
    ÅĽÄĩ
    0.05
    Activations Density 0.026%

    No Known Activations