© 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. 77148
    Prev
    Next
    INDEX
    Explanations

    periods indicating the end of sentences or statements

    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
    èħ°
    -0.07
    umbo
    -0.06
    avic
    -0.06
    تا
    -0.06
     Arthropoda
    -0.06
    éal
    -0.06
    piler
    -0.06
     reap
    -0.06
    ardy
    -0.06
    decorators
    -0.06
    POSITIVE LOGITS
     éĻ
    0.06
    587
    0.06
     Cla
    0.06
     Rue
    0.06
     Branch
    0.05
    oftware
    0.05
    uf
    0.05
    ãİ
    0.05
     DISCLAIM
    0.05
    IGO
    0.05
    Activations Density 0.000%

    No Known Activations