© 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. 15-LLAMASCOPE-RES-131K
    11. 834
    Prev
    Next
    INDEX
    Explanations

    HTML elements and structure in web documents

    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
    ipple
    -0.07
    icut
    -0.07
    imir
    -0.07
    á»ĩu
    -0.07
    iske
    -0.07
    å¾½
    -0.07
    mented
    -0.06
    ythe
    -0.06
    ANTE
    -0.06
    yz
    -0.06
    POSITIVE LOGITS
    aches
    0.07
    otes
    0.06
    ing
    0.06
    ipi
    0.06
     Tucker
    0.06
    maz
    0.06
     Fuller
    0.06
     Gund
    0.05
    .ci
    0.05
    ä¸Ģ级
    0.05
    Activations Density 0.001%

    No Known Activations