© 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. 17-LLAMASCOPE-RES-131K
    11. 74635
    Prev
    Next
    INDEX
    Explanations

    URLs and web addresses

    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
    yre
    -0.06
    лон
    -0.06
     OVERRIDE
    -0.06
    coon
    -0.06
     __("
    -0.06
     anti
    -0.05
    énom
    -0.05
    841
    -0.05
    ahoma
    -0.05
     field
    -0.05
    POSITIVE LOGITS
    ichert
    0.08
    ebek
    0.07
    leyen
    0.07
    価
    0.07
    вед
    0.07
    ADDE
    0.06
    ..'
    0.06
    gili
    0.06
    DOG
    0.06
    eller
    0.06
    Activations Density 0.001%

    No Known Activations