Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. MLP Out
    5. 25-LLAMASCOPE-MLP-131K
    6. 72571
    Prev
    Next
    INDEX
    Explanations

    brand names and company identifiers

    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
    -track
    -0.06
    phyl
    -0.06
    sie
    -0.06
     track
    -0.06
    tracks
    -0.06
    gth
    -0.06
     Track
    -0.06
    gor
    -0.06
    ableView
    -0.06
    âĢĮÙĨ
    -0.06
    POSITIVE LOGITS
    YO
    0.07
    æĦ
    0.07
     Yosemite
    0.06
    raq
    0.06
    ahas
    0.06
     Cele
    0.06
    ocz
    0.06
    å²³
    0.06
    iola
    0.06
    adge
    0.06
    Activations Density 0.001%

    No Known Activations