© 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 EvalsExportsAPI 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. 75048
    Prev
    Next
    INDEX
    Explanations

    URL patterns and numerical data in the text

    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
    lian
    -0.08
    erville
    -0.08
    ourg
    -0.07
    áp
    -0.07
    raud
    -0.07
    ãĥ¯ãĥ¼
    -0.07
    éĭ¼
    -0.07
    lev
    -0.07
    jÄĻ
    -0.07
    udent
    -0.07
    POSITIVE LOGITS
     targeted
    0.06
    913
    0.06
     cop
    0.06
     pac
    0.06
     íĿ¬
    0.05
     vaginal
    0.05
    osu
    0.05
     bonded
    0.05
    å±Ģ
    0.05
    wt
    0.05
    Activations Density 0.006%

    No Known Activations