© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90580
    Prev
    Next
    INDEX
    Explanations

    terms and variations related to a specific species of shark

    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
    imei
    -0.09
    -alist
    -0.09
    zos
    -0.09
    ugi
    -0.09
    ADATA
    -0.09
    uguay
    -0.09
    .scalablytyped
    -0.09
    cplusplus
    -0.09
    NetMessage
    -0.08
    βολ
    -0.08
    POSITIVE LOGITS
     introduced
    0.07
     (
    0.06
    1
    0.06
    /
    0.06
     or
    0.06
    a
    0.06
    2
    0.06
     
    0.06
     p
    0.05
     form
    0.05
    Activations Density 0.017%

    No Known Activations