© 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. 95270
    Prev
    Next
    INDEX
    Explanations

    the word "By" at the beginning of sentences or paragraphs

    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
    emble
    -0.07
     Uncomment
    -0.07
    iÄĩ
    -0.07
    anus
    -0.07
    ping
    -0.07
    (åľŁ
    -0.07
    nesia
    -0.07
    нак
    -0.07
    Specifier
    -0.07
    EntryPoint
    -0.07
    POSITIVE LOGITS
     admin
    0.07
     age
    0.06
     default
    0.06
    è´
    0.06
    (By
    0.06
    by
    0.06
    fleet
    0.06
    nock
    0.06
    By
    0.06
     Grace
    0.06
    Activations Density 0.010%

    No Known Activations