© 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. 106624
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Heath" and variations of the word "death."

    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
     Zuk
    -0.08
    hoot
    -0.07
    iore
    -0.07
    andre
    -0.07
    erable
    -0.06
    haft
    -0.06
    arım
    -0.06
    gings
    -0.06
    venta
    -0.06
    udit
    -0.06
    POSITIVE LOGITS
    erton
    0.09
    umu
    0.08
    ley
    0.08
    emb
    0.07
    field
    0.07
    fulness
    0.07
    land
    0.07
    ivet
    0.07
    row
    0.06
    wood
    0.06
    Activations Density 0.004%

    No Known Activations