© 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. 61474
    Prev
    Next
    INDEX
    Explanations

    phrases related to complex narratives and emotional experiences

    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
    uyu
    -0.07
    ISC
    -0.07
    ISK
    -0.07
    lander
    -0.06
    kowski
    -0.06
    rypton
    -0.06
    lando
    -0.06
    ='".
    -0.06
     olduk
    -0.06
    Intialized
    -0.06
    POSITIVE LOGITS
     like
    0.20
     unlike
    0.17
     zoals
    0.15
     Like
    0.14
     nor
    0.13
     wie
    0.13
     como
    0.12
    å¦Ĥ
    0.12
     Unlike
    0.12
    Like
    0.12
    Activations Density 0.095%

    No Known Activations