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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75106
    Prev
    Next
    INDEX
    Explanations

    terms and references related to proteins and their interactions in biological contexts

    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
    avad
    -0.08
    reon
    -0.08
    ajar
    -0.07
    eyse
    -0.07
     Duis
    -0.07
    /rss
    -0.07
    illery
    -0.06
    OpenHelper
    -0.06
     eof
    -0.06
    llum
    -0.06
    POSITIVE LOGITS
     project
    0.06
    sher
    0.06
    iT
    0.06
     Stam
    0.06
    ots
    0.06
    _paper
    0.06
     sami
    0.06
     Project
    0.06
    à¥Ĥस
    0.05
     soaring
    0.05
    Activations Density 0.221%

    No Known Activations