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. 22-LLAMASCOPE-RES-131K
    6. 5548
    Prev
    Next
    INDEX
    Explanations

    phrases related to offering advice and practical tips

    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
    ogl
    -0.07
    again
    -0.06
    ĨĴ
    -0.06
     Sil
    -0.05
     again
    -0.05
    hist
    -0.05
    ká
    -0.05
    æĪª
    -0.05
    acy
    -0.05
    imest
    -0.05
    POSITIVE LOGITS
    以ä¸ĭ
    0.12
     following
    0.12
     Here
    0.11
    following
    0.11
     Below
    0.11
     Following
    0.11
     follow
    0.10
     here
    0.10
    Here
    0.10
     follows
    0.10
    Activations Density 0.048%

    No Known Activations