© 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 EvalsExportsinterp-engineNEWAPI 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. 5602
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate occurrence or arrival

    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
     Tot
    -0.05
    nie
    -0.05
     son
    -0.05
    uch
    -0.05
     Trials
    -0.05
     supposed
    -0.05
    jin
    -0.05
     Byz
    -0.05
     Dixon
    -0.05
     Dav
    -0.05
    POSITIVE LOGITS
    ÃĹ↵↵
    0.08
    aaS
    0.08
    umper
    0.07
     çĬ
    0.07
    OPS
    0.07
    593
    0.07
     çĪ
    0.07
     hÃłng
    0.07
    JAVA
    0.07
    edium
    0.07
    Activations Density 0.025%

    No Known Activations