© 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. 9-LLAMASCOPE-RES-131K
    11. 95504
    Prev
    Next
    INDEX
    Explanations

    programming terminology and code constructs related to networking and structure definitions

    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
    oj
    -0.06
    edar
    -0.06
    aft
    -0.06
     Whites
    -0.06
     Lau
    -0.06
     Wonder
    -0.06
    ij
    -0.06
     Trevor
    -0.05
    yan
    -0.05
     Rig
    -0.05
    POSITIVE LOGITS
    .appspot
    0.08
    _UT
    0.08
    _CF
    0.08
    ÎĮ
    0.07
    Occurs
    0.07
    opis
    0.07
    欲
    0.07
     اÙĦرÙħزÙĬØ©
    0.07
    adro
    0.07
    EFA
    0.07
    Activations Density 0.037%

    No Known Activations