© 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. 54890
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'w' at various frequencies throughout the document

    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
    ait
    -0.07
    echn
    -0.07
    hd
    -0.07
    ayas
    -0.07
    iations
    -0.06
    ematic
    -0.06
    oved
    -0.06
    ipt
    -0.06
    863
    -0.06
     Bren
    -0.06
    POSITIVE LOGITS
     Ballard
    0.07
    igner
    0.07
    heels
    0.07
    ijken
    0.06
    agner
    0.06
    ulf
    0.06
     wet
    0.06
    ARP
    0.06
    ingers
    0.06
    inger
    0.06
    Activations Density 0.023%

    No Known Activations