© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 74299
    Prev
    Next
    INDEX
    Explanations

    specific names or references to the location "Crawford."

    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
    intr
    -0.07
    ngr
    -0.06
     Mã
    -0.06
    657
    -0.06
    uing
    -0.06
    aravel
    -0.06
    imeter
    -0.06
    513
    -0.06
    umin
    -0.06
     podp
    -0.06
    POSITIVE LOGITS
    ford
    0.08
    urlencode
    0.07
    .githubusercontent
    0.06
    eton
    0.06
    orld
    0.06
    vale
    0.06
    sville
    0.06
    .listFiles
    0.06
     SCT
    0.06
     Ulus
    0.06
    Activations Density 0.004%

    No Known Activations