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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 96213
    Prev
    Next
    INDEX
    Explanations

    concepts related to collaboration and alternative economic systems

    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
    sei
    -0.09
    iot
    -0.08
     Constructs
    -0.07
    hea
    -0.07
    aub
    -0.07
    maries
    -0.06
    LookAndFeel
    -0.06
    DataTask
    -0.06
    zl
    -0.06
    isseur
    -0.06
    POSITIVE LOGITS
    olini
    0.06
    ä¹Ĺ
    0.06
     æĽ
    0.06
    ONG
    0.06
    شب
    0.06
     inspir
    0.06
    .Persistent
    0.06
    olec
    0.06
    .builders
    0.06
     networks
    0.06
    Activations Density 0.001%

    No Known Activations