© 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 EvalsExportsinterp-engineNEWAPI 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. 95501
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the process of explanation or elaboration

    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
    anto
    -0.06
    cken
    -0.06
    aptive
    -0.06
     nowhere
    -0.06
    ald
    -0.06
     clarified
    -0.06
    ille
    -0.05
    no
    -0.05
    orne
    -0.05
     Som
    -0.05
    POSITIVE LOGITS
     anymore
    0.11
     details
    0.09
    Segue
    0.08
    详
    0.08
     further
    0.08
    details
    0.08
     nor
    0.08
     подÑĢоб
    0.08
     here
    0.08
    ossier
    0.08
    Activations Density 0.018%

    No Known Activations