© 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. 17-LLAMASCOPE-RES-131K
    11. 120950
    Prev
    Next
    INDEX
    Explanations

    sections that reference publication details or identifiers

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

    Citation and bibliographic reference information, including page numbers, publication years, DOI identifiers, and URLs in academic or reference texts.

    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
    yy
    -0.06
    à¤ķन
    -0.06
     Gui
    -0.06
     Dag
    -0.06
    Modifiers
    -0.06
    lop
    -0.06
    antt
    -0.05
     Cousins
    -0.05
     imm
    -0.05
     od
    -0.05
    POSITIVE LOGITS
    ATS
    0.07
    amaz
    0.07
    istrovstvÃŃ
    0.07
    ypass
    0.07
    DOI
    0.07
    ë³ij
    0.07
    miner
    0.07
    .slim
    0.06
    hani
    0.06
     DOI
    0.06
    Activations Density 0.008%

    No Known Activations