© 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. 118876
    Prev
    Next
    INDEX
    Explanations

    content related to cultural or artistic themes

    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
     Johannes
    -0.07
    ff
    -0.07
    er
    -0.06
    ammer
    -0.06
     Marshall
    -0.06
    ummer
    -0.06
    ora
    -0.06
    am
    -0.06
    gin
    -0.06
    ISC
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.10
    ake
    0.09
    enaire
    0.08
    ä¹ĭä¸Ģ
    0.08
     addCriterion
    0.08
    ÃŃcul
    0.08
    /full
    0.08
    _codegen
    0.08
    åŃĺäºİ
    0.08
     tá»Ń
    0.07
    Activations Density 0.006%

    No Known Activations