© 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. 129999
    Prev
    Next
    INDEX
    Explanations

    phrases indicating structured processes or methodologies

    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
    ordo
    -0.07
    ecs
    -0.07
    oldem
    -0.06
    izr
    -0.06
    azen
    -0.06
    ondo
    -0.06
    ót
    -0.06
    exion
    -0.06
    ever
    -0.06
    xdb
    -0.06
    POSITIVE LOGITS
    anos
    0.07
     fully
    0.07
     beyond
    0.07
    ushima
    0.07
     Tape
    0.06
    ?url
    0.06
    اÙĨÛĮ
    0.06
    IMIT
    0.06
     actively
    0.06
     stab
    0.06
    Activations Density 0.000%

    No Known Activations