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. 43542
    Prev
    Next
    INDEX
    Explanations

    content related to legal terms and liability issues

    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
    enburg
    -0.06
     rang
    -0.06
    âm
    -0.06
    âu
    -0.06
     Investigation
    -0.06
    ysa
    -0.06
    æĮģãģ¡
    -0.06
    ÅĻeh
    -0.06
     bombed
    -0.06
    iais
    -0.06
    POSITIVE LOGITS
     consequential
    0.17
     punitive
    0.16
     incidental
    0.15
     exemplary
    0.14
     indirect
    0.13
     compens
    0.13
     CONSEQUENTIAL
    0.13
     INCIDENTAL
    0.13
     damages
    0.12
     EXEMPLARY
    0.12
    Activations Density 0.005%

    No Known Activations