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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 90698
    Prev
    Next
    INDEX
    Explanations

    titles and positions of authority within organizations

    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
    issen
    -0.07
    ars
    -0.06
    amm
    -0.06
    ega
    -0.06
    aren
    -0.06
    oppers
    -0.06
    uela
    -0.06
    annon
    -0.06
    official
    -0.06
     Mits
    -0.06
    POSITIVE LOGITS
     Bail
    0.06
    reate
    0.06
    -www
    0.06
    ridged
    0.06
    agram
    0.06
    åħ¼
    0.06
    елÑĮзÑı
    0.06
    _apps
    0.06
     Grü
    0.06
     Lip
    0.06
    Activations Density 0.039%

    No Known Activations