© 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. 54686
    Prev
    Next
    INDEX
    Explanations

    personal connections and interactions within various contexts

    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
    ymax
    -0.08
    hev
    -0.07
    askell
    -0.07
    longleftrightarrow
    -0.07
    ä¸Ģ缴
    -0.07
    ì§ĢëĬĶ
    -0.07
    .Binding
    -0.07
    ibold
    -0.07
    pluck
    -0.07
    umd
    -0.07
    POSITIVE LOGITS
     become
    0.19
     becomes
    0.18
     became
    0.18
     becoming
    0.17
    bec
    0.16
     Become
    0.14
     Became
    0.14
    åıĺå¾Ĺ
    0.13
    Become
    0.13
     soon
    0.12
    Activations Density 0.063%

    No Known Activations