© 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. 28948
    Prev
    Next
    INDEX
    Explanations

    concepts related to social and economic systems

    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
    irt
    -0.07
    ?url
    -0.06
    ado
    -0.06
     Shelter
    -0.06
    ัà¸ģà¸ģ
    -0.06
     dále
    -0.06
    akan
    -0.06
    eken
    -0.06
    adam
    -0.06
    idden
    -0.06
    POSITIVE LOGITS
    anship
    0.08
    iglia
    0.07
    otre
    0.07
    å¸Ń
    0.07
    inion
    0.07
    GMEM
    0.07
    åı«
    0.07
    assage
    0.07
    essions
    0.07
    anness
    0.06
    Activations Density 0.050%

    No Known Activations