© 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. 9-LLAMASCOPE-RES-131K
    11. 95155
    Prev
    Next
    INDEX
    Explanations

    references to item displays or contributions

    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
    aud
    -0.08
    utton
    -0.07
    elial
    -0.06
    egot
    -0.06
    drag
    -0.06
    ermint
    -0.06
    سر
    -0.05
    egan
    -0.05
    chts
    -0.05
     Aud
    -0.05
    POSITIVE LOGITS
    ÐļТ
    0.07
    èĸ
    0.07
    unner
    0.07
    chas
    0.07
    nÃŃku
    0.07
    ×ķ
    0.07
    cete
    0.07
    ibraries
    0.06
    ilere
    0.06
    åħ
    0.06
    Activations Density 0.001%

    No Known Activations