© 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. 76852
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax related to programming functions and classes

    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
    oret
    -0.08
     Bans
    -0.07
    isman
    -0.07
    ault
    -0.07
    velopment
    -0.06
    ubre
    -0.06
    izzard
    -0.06
    peater
    -0.06
    ´Ŀ
    -0.06
    orelease
    -0.06
    POSITIVE LOGITS
    mith
    0.08
    ovÃŃ
    0.06
    ÃĸL
    0.06
     Kür
    0.06
     célib
    0.06
     Düny
    0.06
    die
    0.06
    ｡
    0.06
    courses
    0.06
     prostitu
    0.06
    Activations Density 0.016%

    No Known Activations