© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56769
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or limits to certain concepts or actions

    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
    ima
    -0.07
    er
    -0.07
    ets
    -0.06
    ionario
    -0.06
    IAS
    -0.06
    il
    -0.06
    zers
    -0.06
     Malone
    -0.06
    acÃŃ
    -0.06
     Bere
    -0.05
    POSITIVE LOGITS
    brig
    0.08
    ãĥ³ãĥij
    0.07
    üm
    0.07
    CED
    0.07
    Ctrls
    0.07
    ãĤĵãģª
    0.07
    ãĥ³ãĥIJ
    0.07
    ngth
    0.06
     nÃło
    0.06
    ä¹İ
    0.06
    Activations Density 0.004%

    No Known Activations