Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43666
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "guilty pleasures."

    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
    egra
    -0.08
    ghi
    -0.07
    uevo
    -0.07
    еÑĢо
    -0.07
    amiento
    -0.07
    sg
    -0.07
    pu
    -0.07
    fusion
    -0.07
    iginal
    -0.06
    mare
    -0.06
    POSITIVE LOGITS
     pleasures
    0.14
     pleasure
    0.13
     plea
    0.12
     pleas
    0.11
     conscience
    0.11
     Ple
    0.11
     verdict
    0.10
     trip
    0.10
     Trip
    0.10
     parties
    0.09
    Activations Density 0.009%

    No Known Activations