© 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. 83400
    Prev
    Next
    INDEX
    Explanations

    information regarding logistics and arrangements

    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
    iling
    -0.07
    statt
    -0.06
    adal
    -0.06
    752
    -0.06
    celik
    -0.06
     Oro
    -0.06
    ardon
    -0.06
    atum
    -0.06
    hm
    -0.06
    ulg
    -0.06
    POSITIVE LOGITS
     shortly
    0.08
     upon
    0.08
     Shortly
    0.07
    Upon
    0.07
    Shortly
    0.07
     Upon
    0.07
    abd
    0.07
    ÏĨÏĮ
    0.07
    Ŀ
    0.07
    agli
    0.07
    Activations Density 0.014%

    No Known Activations