© 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. 130469
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about various topics

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

    Question-answer format where "What is X?" introduces a definition or explanation about the topic X.

    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
    itud
    -0.06
    Ư
    -0.06
    aise
    -0.06
     Birch
    -0.06
    acles
    -0.06
    lic
    -0.06
    itudes
    -0.06
    zeÅĦ
    -0.06
     Cald
    -0.05
    atee
    -0.05
    POSITIVE LOGITS
     çŃĶ
    0.08
     Answer
    0.08
     basically
    0.08
    çŃĶ
    0.08
     ANSW
    0.08
     billeder
    0.07
     answer
    0.07
    Це
    0.07
    æĺ¯ä¸Ģ
    0.07
    eday
    0.07
    Activations Density 0.015%

    No Known Activations