© 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. 60122
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of the word "you."

    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
    oui
    -0.08
     Tato
    -0.07
    że
    -0.07
    rophe
    -0.07
    ège
    -0.07
     bé
    -0.07
    chem
    -0.07
    ãĥĵãĥ¼
    -0.06
    ÑĦоÑĢÑĤ
    -0.06
    ged
    -0.06
    POSITIVE LOGITS
     gonna
    0.08
     sure
    0.08
    gon
    0.06
    'e
    0.06
     own
    0.06
    Sure
    0.06
     Sure
    0.06
    onth
    0.06
    pressive
    0.06
    avour
    0.06
    Activations Density 0.022%

    No Known Activations