© 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. 95499
    Prev
    Next
    INDEX
    Explanations

    questions and themes relating to self-identity and personal reflection

    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
    ù
    -0.07
    uras
    -0.07
    £
    -0.07
    лÑİб
    -0.07
    ¦æĥħ
    -0.06
     kys
    -0.06
    FormsModule
    -0.06
    icer
    -0.06
    onden
    -0.06
    à¥Ģà¤Ł
    -0.06
    POSITIVE LOGITS
     lately
    0.07
    ìĹĦ
    0.06
    riter
    0.06
    velop
    0.06
    marshal
    0.06
    $__
    0.06
     others
    0.05
     lst
    0.05
    izia
    0.05
    Uni
    0.05
    Activations Density 0.004%

    No Known Activations