© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 93675
    Prev
    Next
    INDEX
    Explanations

    elements related to Java or Spring framework coding

    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
    urai
    -0.08
     èĩªåĬ¨çĶŁæĪIJ
    -0.07
     Gib
    -0.06
    Serialized
    -0.06
    _alt
    -0.06
    MW
    -0.06
     repro
    -0.06
    ¶
    -0.06
    �
    -0.05
     Ud
    -0.05
    POSITIVE LOGITS
    fen
    0.08
    .weixin
    0.08
    wechat
    0.07
    jie
    0.07
    .baidu
    0.07
     baise
    0.07
     layui
    0.07
    uniacid
    0.07
    jian
    0.07
    ï¼Ľ↵
    0.07
    Activations Density 0.191%

    No Known Activations