© 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. 57847
    Prev
    Next
    INDEX
    Explanations

    key geographic locations and cultural landmarks

    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
    à¸Ľà¸£à¸°à¸Ĭ
    -0.07
    à¹Ħหà¸Ļ
    -0.07
    iddi
    -0.07
    ÏģÏį
    -0.06
    urve
    -0.06
    atel
    -0.06
    ÚĨÙĩ
    -0.06
    ertos
    -0.06
    иÑĤоÑĢ
    -0.06
    orgot
    -0.06
    POSITIVE LOGITS
     today
    0.06
    ÑĢик
    0.06
    çĶŁ
    0.06
    once
    0.06
    ãĥ¼ãĥ³
    0.05
    QUIRE
    0.05
    ÑĢÑĮ
    0.05
     followed
    0.05
    ó
    0.05
     afternoon
    0.05
    Activations Density 0.020%

    No Known Activations