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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70051
    Prev
    Next
    INDEX
    Explanations

    entities and actions related to legislative processes and parliamentary activities

    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
     Bd
    -0.07
    áct
    -0.06
    redo
    -0.06
    ãĤ¿ãĥ¼
    -0.06
    enek
    -0.06
    ahlen
    -0.06
     Milton
    -0.06
    iaux
    -0.06
    áp
    -0.06
     veget
    -0.05
    POSITIVE LOGITS
     session
    0.09
     motion
    0.08
    ãĤ¤ãĤ¯
    0.07
     fas
    0.07
     bill
    0.07
     Speaker
    0.07
     floor
    0.07
     èŃ
    0.07
     pl
    0.07
     bills
    0.07
    Activations Density 0.005%

    No Known Activations