© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 130066
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or expressions of deficiency

    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
     McCart
    -0.07
     CWE
    -0.07
     Technology
    -0.07
    813
    -0.07
    üstü
    -0.06
     favourite
    -0.06
    ï¿
    -0.06
    814
    -0.06
    userdata
    -0.06
    501
    -0.06
    POSITIVE LOGITS
    atever
    0.07
     array
    0.06
    ArrayType
    0.06
     pronto
    0.06
     meantime
    0.06
    otas
    0.06
    ilter
    0.06
    å¹²
    0.06
    cies
    0.05
     overall
    0.05
    Activations Density 0.000%

    No Known Activations