© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 128644
    Prev
    Next
    INDEX
    Explanations

    instances of competition and adversity

    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
    amoto
    -0.08
    åĩĮ
    -0.07
    .si
    -0.07
     Ekon
    -0.07
    exas
    -0.07
    ãĥ¼ãĥł
    -0.07
    .Extension
    -0.07
    ÑĢÑĥÑĪ
    -0.07
    _MT
    -0.07
    داد
    -0.07
    POSITIVE LOGITS
     departure
    0.08
    vac
    0.08
     abs
    0.07
     depart
    0.07
     absent
    0.07
     losses
    0.07
    loss
    0.07
     original
    0.07
     retire
    0.07
     leave
    0.07
    Activations Density 0.115%

    No Known Activations