© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76074
    Prev
    Next
    INDEX
    Explanations

    words associated with strong emotions and characteristics

    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
    ä¿
    -0.07
    nim
    -0.07
     STRICT
    -0.07
    ãĥIJãĥ¼
    -0.07
    严
    -0.07
    .me
    -0.06
    995
    -0.06
    èĬĻ
    -0.06
    بÙĦ
    -0.06
    åIJĪ
    -0.06
    POSITIVE LOGITS
     detail
    0.09
     ways
    0.08
     fashion
    0.08
    detail
    0.07
     circumstances
    0.07
     proportions
    0.07
     conditions
    0.06
     surroundings
    0.06
    ISON
    0.06
     Detail
    0.06
    Activations Density 0.047%

    No Known Activations