© 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. 75270
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration and community-building initiatives

    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
    enville
    -0.06
    rax
    -0.06
    DAT
    -0.06
     Julius
    -0.06
    RAP
    -0.06
    ä¸ĺ
    -0.06
    igue
    -0.06
    iros
    -0.06
     majority
    -0.06
     inf
    -0.06
    POSITIVE LOGITS
    arges
    0.08
     lorem
    0.07
    ÑĪев
    0.07
     hereby
    0.07
    ác
    0.07
     Lorem
    0.07
    .fc
    0.07
     kami
    0.07
    mers
    0.06
    emit
    0.06
    Activations Density 0.001%

    No Known Activations