© 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. 61265
    Prev
    Next
    INDEX
    Explanations

    instances of contrasting statements or phrases

    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
    üp
    -0.08
    795
    -0.07
    à¹Ħหà¸Ļ
    -0.06
    own
    -0.06
    iclass
    -0.06
    ÙĪÙĨÙĩ
    -0.06
    ertino
    -0.06
    lops
    -0.06
    unos
    -0.06
     ÑĥÑĩаÑģÑĤи
    -0.06
    POSITIVE LOGITS
     maybe
    0.10
     Maybe
    0.08
    Maybe
    0.08
    maybe
    0.07
    dek
    0.07
    eker
    0.06
     vielleicht
    0.06
     tot
    0.06
    elow
    0.06
    ÑĢаÑģÑĤ
    0.06
    Activations Density 0.032%

    No Known Activations