© 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. 129386
    Prev
    Next
    INDEX
    Explanations

    references to the name "Alfred."

    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
    elsey
    -0.07
    eldom
    -0.07
    _EXTERN
    -0.07
    upp
    -0.06
    upe
    -0.06
    ethyst
    -0.06
    reon
    -0.06
    ifen
    -0.06
    utherland
    -0.06
    ynchronous
    -0.06
    POSITIVE LOGITS
    o
    0.10
    reesome
    0.07
    itious
    0.07
    ious
    0.07
    raj
    0.07
    yt
    0.07
    inho
    0.07
    onya
    0.07
    arms
    0.07
     Hiç
    0.06
    Activations Density 0.004%

    No Known Activations