© 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. 83133
    Prev
    Next
    INDEX
    Explanations

    sections that provide a summary or general information about the context or background

    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
    allet
    -0.07
    ãģ£ãģ¡
    -0.07
    oner
    -0.06
     Newman
    -0.06
     Hindered
    -0.06
    /Dk
    -0.06
    ãĥ¼ãĥĭ
    -0.06
    ÙĩرÙĩ
    -0.06
    htar
    -0.06
    EMA
    -0.06
    POSITIVE LOGITS
     ÐĴики
    0.07
    veled
    0.07
    ken
    0.06
    eum
    0.06
    /rfc
    0.06
    ora
    0.06
     exercise
    0.06
    _pref
    0.06
    uggle
    0.06
    驾
    0.06
    Activations Density 0.000%

    No Known Activations