© 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. 15-LLAMASCOPE-RES-131K
    11. 62310
    Prev
    Next
    INDEX
    Explanations

    references to election processes and voter assistance

    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
    anni
    -0.07
    azar
    -0.07
     Guest
    -0.06
    ãĤ·ãĤ¢
    -0.06
    SystemService
    -0.06
    anse
    -0.06
     ullam
    -0.06
     Slee
    -0.06
    ollower
    -0.06
    ieres
    -0.06
    POSITIVE LOGITS
     volunteers
    0.08
    elu
    0.07
     early
    0.07
     volunteer
    0.06
     Early
    0.06
    early
    0.06
     hours
    0.06
    yl
    0.06
    iv
    0.06
     Marathon
    0.06
    Activations Density 0.010%

    No Known Activations