© 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. 9-LLAMASCOPE-RES-131K
    11. 98088
    Prev
    Next
    INDEX
    Explanations

    specific phrases or terms related to community resources and support initiatives

    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
    sex
    -0.07
    essen
    -0.06
    ione
    -0.06
    ROS
    -0.06
    æĦıæĢĿ
    -0.06
    PushButton
    -0.06
    engl
    -0.06
     Playboy
    -0.06
    afe
    -0.06
    æĺ
    -0.06
    POSITIVE LOGITS
     âĸ²
    0.07
    áº
    0.07
    Äįin
    0.07
    riday
    0.06
    746
    0.06
    totals
    0.06
    itmap
    0.06
    ickest
    0.06
    itura
    0.06
    ebek
    0.06
    Activations Density 0.032%

    No Known Activations