© 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. 5-LLAMASCOPE-RES-131K
    11. 125783
    Prev
    Next
    INDEX
    Explanations

    comparisons and statements that emphasize an increase or superiority in a characteristic

    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
    ikh
    -0.07
    uong
    -0.06
    -bearing
    -0.06
    349
    -0.06
    arken
    -0.06
    edral
    -0.06
     premises
    -0.06
     Bry
    -0.06
    ajo
    -0.06
    urs
    -0.06
    POSITIVE LOGITS
     пÑĢоз
    0.07
    оÑĢи
    0.07
    IFO
    0.07
    IPA
    0.07
    Cum
    0.07
    est
    0.07
    bz
    0.07
    TableCell
    0.07
     Slee
    0.06
     Julien
    0.06
    Activations Density 0.002%

    No Known Activations