© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118374
    Prev
    Next
    INDEX
    Explanations

    technical language related to cloud computing and data processing

    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
    adera
    -0.07
    Ø´ÛĮ
    -0.07
    assing
    -0.06
     Fus
    -0.06
    udes
    -0.06
    greg
    -0.06
    122
    -0.06
    _regularizer
    -0.06
    azard
    -0.06
    uitka
    -0.06
    POSITIVE LOGITS
     client
    0.13
     clients
    0.12
    client
    0.11
    clients
    0.11
    -client
    0.10
     Clients
    0.10
    客æĪ·
    0.10
    .client
    0.10
     Client
    0.10
     klient
    0.09
    Activations Density 0.124%

    No Known Activations