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. 5480
    Prev
    Next
    INDEX
    Explanations

    patterns of repetition or consistency in information

    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
    s
    -0.09
    ÛĮا
    -0.08
    teenth
    -0.08
    eing
    -0.08
    ëģĶ
    -0.08
    _RCC
    -0.07
    iÅŁ
    -0.07
    Ùĩ
    -0.07
    sı
    -0.07
    .EventArgs
    -0.07
    POSITIVE LOGITS
    ly
    0.12
    LY
    0.09
    ÑģÑı
    0.08
    theless
    0.08
    nd
    0.08
    forward
    0.07
    Ø©
    0.07
    ../
    0.07
    forth
    0.07
    ily
    0.07
    Activations Density 0.033%

    No Known Activations