© 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. 31076
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to" and its derivatives in various forms

    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
    èŃ
    -0.07
    tü
    -0.06
     Preston
    -0.06
     Tune
    -0.06
     somebody
    -0.06
    0
    -0.06
    vern
    -0.05
     proven
    -0.05
    isco
    -0.05
     tune
    -0.05
    POSITIVE LOGITS
     accomplish
    0.08
     Liberties
    0.08
    å®ĮæĪIJ
    0.08
     completing
    0.08
     IMPLEMENT
    0.07
    Comple
    0.07
    ea
    0.07
    .execute
    0.07
     process
    0.07
    GRAM
    0.07
    Activations Density 0.040%

    No Known Activations