© 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. 125611
    Prev
    Next
    INDEX
    Explanations

    elements related to conflict and interpersonal dynamics

    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
    ecast
    -0.08
    uracy
    -0.07
    rame
    -0.07
    iaÅĤa
    -0.07
     takson
    -0.07
    è¿·
    -0.07
    ãģĮãģĤãģ£ãģŁ
    -0.07
    edef
    -0.07
    odic
    -0.07
    hti
    -0.07
    POSITIVE LOGITS
     ""
    0.06
     Bull
    0.06
    )->
    0.06
     while
    0.06
     Moor
    0.06
    #ab
    0.06
     but
    0.06
     courtesy
    0.06
    eck
    0.05
     Courtesy
    0.05
    Activations Density 0.067%

    No Known Activations