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. MLP Out
    5. 29-LLAMASCOPE-MLP-131K
    6. 5076
    Prev
    Next
    INDEX
    Explanations

    phrases related to pricing, particularly costs per unit

    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
    angles
    -0.07
    phabet
    -0.06
     bash
    -0.06
     =>$
    -0.06
    bash
    -0.06
    eron
    -0.06
     alphabet
    -0.06
    older
    -0.06
    vect
    -0.06
    åIJ¾
    -0.06
    POSITIVE LOGITS
     sinc
    0.07
    aea
    0.07
    cac
    0.06
    olini
    0.06
    å¾Ħ
    0.06
    λλη
    0.06
     Fol
    0.06
    artz
    0.06
    cela
    0.06
    phinx
    0.06
    Activations Density 0.001%

    No Known Activations