© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118513
    Prev
    Next
    INDEX
    Explanations

    references to euphemisms and swearing

    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
    ByExample
    -0.07
    acon
    -0.07
    ervals
    -0.07
     deduct
    -0.06
    hazi
    -0.06
    inden
    -0.06
    796
    -0.06
     slash
    -0.06
    unan
    -0.06
    ee
    -0.06
    POSITIVE LOGITS
     hur
    0.07
     à¤ħश
    0.07
    abin
    0.07
     taboo
    0.07
     ÑĥпоÑĤÑĢеб
    0.07
     offensive
    0.06
     Offensive
    0.06
     ejected
    0.06
    污
    0.06
    ç
    0.06
    Activations Density 0.022%

    No Known Activations