© 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. 9-LLAMASCOPE-RES-131K
    11. 96425
    Prev
    Next
    INDEX
    Explanations

    descriptions of magical or extraordinary experiences

    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
    PCP
    -0.07
    inis
    -0.07
    ,
    -0.06
    asca
    -0.06
     orthogonal
    -0.06
    mdb
    -0.06
    agnar
    -0.06
    ons
    -0.06
    /or
    -0.05
    erland
    -0.05
    POSITIVE LOGITS
    ãĢģ“
    0.08
    ॰
    0.07
    Ł
    0.07
    973
    0.07
     باÙĤ
    0.07
    .opendaylight
    0.07
    εί
    0.07
     конÑĤÑĢа
    0.06
    annels
    0.06
    ÑĢÑĸÑĪ
    0.06
    Activations Density 0.170%

    No Known Activations