© 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. 9-LLAMASCOPE-RES-131K
    11. 98692
    Prev
    Next
    INDEX
    Explanations

    punctuation marks at the end of sentences

    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
    uras
    -0.09
     hrom
    -0.08
    cken
    -0.08
    alien
    -0.07
    ,âĢ¦↵↵
    -0.07
    ÏĦε
    -0.07
    çµ
    -0.07
    elsing
    -0.07
    ÑĢÑĸй
    -0.07
    uilt
    -0.06
    POSITIVE LOGITS
    enville
    0.07
    ebi
    0.07
    orative
    0.06
    yll
    0.06
    ffen
    0.06
    ingular
    0.06
    adele
    0.06
    razione
    0.06
     Chand
    0.05
     Deferred
    0.05
    Activations Density 0.106%

    No Known Activations