© 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. 41005
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

    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
    Ã
    -0.07
    bero
    -0.07
    äng
    -0.07
    ürn
    -0.07
    antan
    -0.07
    orz
    -0.07
    duino
    -0.06
    alat
    -0.06
    HASH
    -0.06
    iosper
    -0.06
    POSITIVE LOGITS
    å¹¹ç·ļ
    0.07
    ObjectType
    0.07
    unas
    0.07
    iew
    0.06
    opoulos
    0.06
     Jr
    0.06
    woke
    0.06
     sil
    0.06
    idos
    0.06
    ové
    0.06
    Activations Density 0.004%

    No Known Activations