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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 130619
    Prev
    Next
    INDEX
    Explanations

    references to research-based findings and methodologies

    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
    ycz
    -0.08
    uled
    -0.07
    Ïģη
    -0.07
     klu
    -0.07
     ucz
    -0.07
    owie
    -0.07
    tent
    -0.07
    ä¼Ŀ
    -0.06
    oksen
    -0.06
    stroy
    -0.06
    POSITIVE LOGITS
     experience
    0.10
     research
    0.09
     experiences
    0.09
     data
    0.08
     personal
    0.08
     interviews
    0.08
     recent
    0.07
     real
    0.07
     field
    0.07
     case
    0.07
    Activations Density 0.011%

    No Known Activations