© 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. 104470
    Prev
    Next
    INDEX
    Explanations

    construction-related verbs indicating actions and processes

    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
    laus
    -0.08
    á»ĥn
    -0.07
    iek
    -0.07
    æĺ¯ä¸Ģ个
    -0.07
    618
    -0.07
    #ac
    -0.06
    .VK
    -0.06
    ãĤį
    -0.06
    ,arg
    -0.06
     mü
    -0.06
    POSITIVE LOGITS
     Dol
    0.07
    olang
    0.07
    ±Ð¾ÑĤ
    0.06
    íķ´
    0.06
    /apis
    0.06
    otten
    0.06
    antz
    0.06
    ateria
    0.06
     Fu
    0.06
    avia
    0.06
    Activations Density 0.048%

    No Known Activations