© 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. 77084
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and documentation terminology

    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
    à¤Ĺल
    -0.07
    amina
    -0.07
    imitive
    -0.07
    ähl
    -0.07
    çĨ
    -0.07
    æĺĵ
    -0.06
    ermal
    -0.06
    pageTitle
    -0.06
    ToObject
    -0.06
    Ãłm
    -0.06
    POSITIVE LOGITS
    aan
    0.06
     SIL
    0.06
    /vnd
    0.06
    ors
    0.06
    doing
    0.06
    oster
    0.06
     EntityState
    0.06
    keterangan
    0.06
    ets
    0.06
    /UIKit
    0.06
    Activations Density 0.000%

    No Known Activations