© 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. 76190
    Prev
    Next
    INDEX
    Explanations

    various descriptors indicating quality and scale in contexts of projects, performances, and relationships

    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
    ernaut
    -0.06
    биÑĤ
    -0.06
    dit
    -0.06
    mania
    -0.06
    боÑĤ
    -0.06
    caler
    -0.06
    rchive
    -0.06
    ason
    -0.06
    .GraphicsUnit
    -0.06
    ongyang
    -0.06
    POSITIVE LOGITS
     tão
    0.09
    è¿Ļä¹Ī
    0.09
     à¤ĩतन
    0.08
    ãģĵãĤĵãģª
    0.07
    å¦ĤæѤ
    0.07
    zept
    0.07
     amount
    0.06
    è¨Ī
    0.06
    ç«
    0.06
     such
    0.06
    Activations Density 0.032%

    No Known Activations