© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75844
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lecture" and related terms

    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
    å¤ķ
    -0.07
    nemonic
    -0.07
    ÏĤ
    -0.07
    SCP
    -0.07
    nen
    -0.07
    ãģĦãĤĭ
    -0.07
    klä
    -0.07
    way
    -0.07
    ildo
    -0.07
    lero
    -0.07
    POSITIVE LOGITS
    hip
    0.08
    tainment
    0.07
    ven
    0.07
    ee
    0.07
    idebar
    0.07
    quire
    0.07
    aper
    0.07
    bubble
    0.07
     Loft
    0.06
    illos
    0.06
    Activations Density 0.005%

    No Known Activations