Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95805
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication technologies and organizational issues

    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
    bjerg
    -0.06
    mir
    -0.05
    ack
    -0.05
    ops
    -0.05
    mist
    -0.05
    sit
    -0.05
    à¸ŀ
    -0.05
    Minute
    -0.05
    Sit
    -0.05
     Hart
    -0.05
    POSITIVE LOGITS
     Rooney
    0.07
     ciz
    0.07
    داÙħ
    0.07
    omo
    0.07
    onu
    0.07
     Invasion
    0.06
    expo
    0.06
    ([]*
    0.06
    ÙĪÙ¾
    0.06
    UNS
    0.06
    Activations Density 0.012%

    No Known Activations