© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 96463
    Prev
    Next
    INDEX
    Explanations

    phrases related to design and submission processes

    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
    vig
    -0.06
    orp
    -0.06
    anou
    -0.06
    олом
    -0.06
     Petty
    -0.06
    _typ
    -0.06
    pta
    -0.06
    igos
    -0.05
    481
    -0.05
    irit
    -0.05
    POSITIVE LOGITS
    ÑĢади
    0.08
     setw
    0.07
    uffed
    0.07
     ç¬
    0.06
    жи
    0.06
    izo
    0.06
    izzo
    0.06
    uba
    0.06
    çŃĭ
    0.06
    FML
    0.06
    Activations Density 0.002%

    No Known Activations