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. 25-LLAMASCOPE-MLP-131K
    6. 72615
    Prev
    Next
    INDEX
    Explanations

    terminology related to audio processing systems and techniques

    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
     Curtain
    -0.07
     Charl
    -0.06
     hurt
    -0.06
     Hurt
    -0.06
    iddi
    -0.06
    Ñĩе
    -0.06
     curtain
    -0.06
    edl
    -0.06
    iminal
    -0.06
    us
    -0.06
    POSITIVE LOGITS
    linkplain
    0.07
    eyer
    0.07
    dojo
    0.07
    ivor
    0.07
    ovo
    0.06
     beden
    0.06
    ardown
    0.06
    ova
    0.06
     norge
    0.06
    umberland
    0.06
    Activations Density 0.189%

    No Known Activations