© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 125809
    Prev
    Next
    INDEX
    Explanations

    instances of the word "planner" and its variations, as well as references to planning or solving in a technical context

    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
    дина
    -0.07
    cete
    -0.07
     feather
    -0.06
    ÌĨ
    -0.06
     princip
    -0.06
    lamaz
    -0.06
    ustil
    -0.06
    lá
    -0.06
     Princip
    -0.06
    oter
    -0.06
    POSITIVE LOGITS
    arts
    0.07
    OutOfRangeException
    0.07
    ific
    0.07
    fu
    0.07
    icontrol
    0.07
    访
    0.06
    \Id
    0.06
    imoto
    0.06
    quo
    0.06
    Ŀ
    0.06
    Activations Density 0.002%

    No Known Activations