© 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. 17-LLAMASCOPE-RES-131K
    11. 17027
    Prev
    Next
    INDEX
    Explanations

    the name "Aaron" in various contexts throughout the text

    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
    pesan
    -0.07
    /stdc
    -0.07
    erman
    -0.07
    yz
    -0.07
    ermen
    -0.07
    gere
    -0.07
    ilib
    -0.07
    esters
    -0.07
    opping
    -0.07
    (íģ¬ê¸°
    -0.07
    POSITIVE LOGITS
    son
    0.07
    hyth
    0.06
    254
    0.06
    emb
    0.06
    net
    0.06
    cad
    0.06
    ensch
    0.06
    ight
    0.06
    tru
    0.06
    otto
    0.06
    Activations Density 0.004%

    No Known Activations