© 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. 72889
    Prev
    Next
    INDEX
    Explanations

    instances of the word "back" and its related expressions

    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
    eniz
    -0.07
    ifu
    -0.07
    iska
    -0.07
     Corpus
    -0.07
    096
    -0.07
     Chop
    -0.07
    appa
    -0.07
    alytics
    -0.07
    ãĥĩãĥ«
    -0.06
    iske
    -0.06
    POSITIVE LOGITS
    éĢĢ
    0.09
    -ret
    0.07
     retreat
    0.07
    /back
    0.07
    wards
    0.07
     назад
    0.06
    òi
    0.06
     Retreat
    0.06
    ä¸ĢæŃ¥
    0.06
    ices
    0.06
    Activations Density 0.023%

    No Known Activations