© 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. 76781
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal validation and licensing requirements

    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
    HITE
    -0.06
    _deinit
    -0.06
    ANI
    -0.06
    tors
    -0.06
    ož
    -0.06
    BEL
    -0.06
    enler
    -0.06
    _fast
    -0.06
    layıcı
    -0.06
    ÙĦب
    -0.06
    POSITIVE LOGITS
    utes
    0.07
    ÌĤ
    0.06
     Gut
    0.06
    .Guna
    0.06
    hai
    0.06
    анÑĮ
    0.06
     leng
    0.06
    uez
    0.06
    cljs
    0.06
    änd
    0.06
    Activations Density 0.001%

    No Known Activations