© 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. 16263
    Prev
    Next
    INDEX
    Explanations

    CSS properties related to layout styling

    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
    ÙĨع
    -0.07
    oog
    -0.07
    lessly
    -0.07
    teg
    -0.07
     bÄĻd
    -0.07
    OLOR
    -0.07
     WINDOWS
    -0.07
    Ñĥг
    -0.07
    .appspot
    -0.07
    icer
    -0.07
    POSITIVE LOGITS
    .generated
    0.07
    fight
    0.06
    owitz
    0.06
    im
    0.06
    они
    0.06
    785
    0.06
    wards
    0.05
    ãĥ³ãĤ¿
    0.05
    tet
    0.05
    stairs
    0.05
    Activations Density 0.003%

    No Known Activations