© 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. 120077
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate attempts to ensure accuracy or quality

    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
    paralle
    -0.06
    æĪ
    -0.06
    herit
    -0.06
    ogui
    -0.06
    ream
    -0.06
    trib
    -0.06
    asm
    -0.06
    atre
    -0.06
    rep
    -0.05
    .mb
    -0.05
    POSITIVE LOGITS
    ãĥĥãĤ«ãĥ¼
    0.08
    εÏį
    0.07
    arkin
    0.07
    SED
    0.07
    -valu
    0.07
    راÙģ
    0.06
    .unique
    0.06
    onic
    0.06
    LIC
    0.06
     tả
    0.06
    Activations Density 0.003%

    No Known Activations