© 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 EvalsExportsAPI 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. 83854
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" in various contexts

    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
     Umb
    -0.06
    ucher
    -0.06
    olla
    -0.06
     initialState
    -0.06
    unami
    -0.06
     &
    -0.06
    monds
    -0.06
    asmus
    -0.06
    863
    -0.06
    erek
    -0.06
    POSITIVE LOGITS
    -equiv
    0.08
    /Documents
    0.07
    imu
    0.07
    .ActionListener
    0.07
    bor
    0.07
    港
    0.07
    imus
    0.07
    usu
    0.07
    su
    0.06
     hÃłng
    0.06
    Activations Density 0.000%

    No Known Activations