© 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. 126718
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Molly"

    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
    oningen
    -0.09
    panse
    -0.08
    .scalablytyped
    -0.08
    inkel
    -0.08
    ĥĿ
    -0.07
    \<^
    -0.07
    ulin
    -0.07
    опÑĢоÑģ
    -0.07
    processable
    -0.07
    -ÑĤо
    -0.07
    POSITIVE LOGITS
    ire
    0.08
    s
    0.08
    hood
    0.07
    ammer
    0.07
    Ùĩ
    0.06
    ares
    0.06
    ileo
    0.06
    ens
    0.06
    ah
    0.06
    are
    0.06
    Activations Density 0.004%

    No Known Activations