© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60793
    Prev
    Next
    INDEX
    Explanations

    words related to mathematical processes or functions

    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
    ubbo
    -0.07
    ео
    -0.07
    esian
    -0.07
    gypt
    -0.07
    ippy
    -0.07
    gd
    -0.06
    ever
    -0.06
    uptools
    -0.06
    ÏĦιν
    -0.06
    .ny
    -0.06
    POSITIVE LOGITS
     va
    0.07
    uze
    0.07
    ysi
    0.06
    elize
    0.06
    STALL
    0.06
    989
    0.06
    ]|[
    0.06
    ivate
    0.06
    inea
    0.06
    ises
    0.06
    Activations Density 0.000%

    No Known Activations