© 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. 80356
    Prev
    Next
    INDEX
    Explanations

    points about personal development and growth over time

    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
    lod
    -0.06
     hadn
    -0.06
    ès
    -0.06
    onium
    -0.06
    .restart
    -0.06
    835
    -0.06
    andy
    -0.06
    kke
    -0.05
    rame
    -0.05
    azzo
    -0.05
    POSITIVE LOGITS
     increasingly
    0.17
    è¶Ĭ
    0.14
     cÃłng
    0.13
     becomes
    0.11
     become
    0.11
    åıĺå¾Ĺ
    0.10
     becoming
    0.10
     Became
    0.10
     increasing
    0.10
     Increasing
    0.10
    Activations Density 0.058%

    No Known Activations