© 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. 76243
    Prev
    Next
    INDEX
    Explanations

    phrases related to political actions and agendas

    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
    ÌĢ
    -0.07
     Tarihi
    -0.07
    zell
    -0.07
    cek
    -0.07
    Advertisement
    -0.07
    ãĥĬãĥ¼
    -0.06
    gesi
    -0.06
    chner
    -0.06
    thouse
    -0.06
    avors
    -0.06
    POSITIVE LOGITS
    åĭ
    0.06
     juris
    0.06
    ırak
    0.06
     Grad
    0.06
     unnamed
    0.05
    lingen
    0.05
     pylint
    0.05
    ¦
    0.05
    ãĥ§
    0.05
    ousse
    0.05
    Activations Density 0.001%

    No Known Activations