Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95923
    Prev
    Next
    INDEX
    Explanations

    verbs related to educational or instructional activities

    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
    ieren
    -0.08
    oken
    -0.08
     localVar
    -0.07
    zano
    -0.07
    ijken
    -0.07
    ãĥ¥ãĥ¼
    -0.07
    ichern
    -0.07
    indhoven
    -0.07
    ctest
    -0.07
    eree
    -0.07
    POSITIVE LOGITS
    šti
    0.06
    .await
    0.06
     breat
    0.06
    rade
    0.05
    ObjectName
    0.05
     curt
    0.05
     acknow
    0.05
    mada
    0.05
    obus
    0.05
     
    0.05
    Activations Density 0.038%

    No Known Activations