© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 78552
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to measurement and evaluation

    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
    /the
    -0.08
    ordin
    -0.08
    ãģĭãģ®
    -0.07
    bye
    -0.07
    /her
    -0.07
    ocket
    -0.07
    -нибÑĥдÑĮ
    -0.07
    меÑĢ
    -0.07
    icket
    -0.07
    iner
    -0.07
    POSITIVE LOGITS
     themselves
    0.14
    (ed
    0.10
     thems
    0.09
    ä¸įäºĨ
    0.09
    leur
    0.08
    [d
    0.08
    çļĦæĺ¯
    0.08
    ANNOT
    0.08
    äºĨä¸Ģ
    0.07
     their
    0.07
    Activations Density 0.419%

    No Known Activations