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. 44321
    Prev
    Next
    INDEX
    Explanations

    non-standard characters and special symbols used in text

    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
    ðŁ
    -0.06
     ðŁ
    -0.06
    ayah
    -0.06
    ðĿ
    -0.06
     ðŁij
    -0.06
    =<?=
    -0.06
        
    -0.06
    ðŁĴ
    -0.05
    tech
    -0.05
     COVID
    -0.05
    POSITIVE LOGITS
     fucking
    0.13
     fucked
    0.12
     fuck
    0.12
     fucks
    0.12
     Fucking
    0.12
     Fuck
    0.11
     shit
    0.11
     FUCK
    0.11
    fuck
    0.11
     generosity
    0.10
    Activations Density 0.003%

    No Known Activations