© 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. 78732
    Prev
    Next
    INDEX
    Explanations

    terms related to political and military contexts

    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
    ils
    -0.06
    ect
    -0.06
    thon
    -0.05
    ibraltar
    -0.05
    ht
    -0.05
    rowad
    -0.05
    ills
    -0.05
    oksen
    -0.05
    yth
    -0.05
    []
    -0.05
    POSITIVE LOGITS
    ฯ
    0.08
    æ³£
    0.07
    ãĤŃãĥ¥
    0.07
    íģ¼
    0.07
     eskort
    0.07
     setBackgroundColor
    0.07
    .setScale
    0.07
    åĺĽ
    0.07
    .echo
    0.07
     outfit
    0.07
    Activations Density 0.030%

    No Known Activations