© 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. 268
    Prev
    Next
    INDEX
    Explanations

    references to candidates and the selection process in a nomination context

    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
    abd
    -0.07
    snap
    -0.07
    strand
    -0.06
    éŀ
    -0.06
    ÑĤÑĢа
    -0.06
     Sok
    -0.06
    gis
    -0.06
    важа
    -0.06
    coni
    -0.06
    allen
    -0.06
    POSITIVE LOGITS
     options
    0.07
    -options
    0.07
     competing
    0.07
    åĢĻ
    0.07
     choices
    0.07
     option
    0.06
    ynos
    0.06
    options
    0.06
     Options
    0.06
     possibilities
    0.06
    Activations Density 0.024%

    No Known Activations