© 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. 78041
    Prev
    Next
    INDEX
    Explanations

    instances of the word "you" and its variations in context

    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
     McGu
    -0.07
    ukes
    -0.07
    aura
    -0.07
    cÃŃm
    -0.07
    anium
    -0.07
    otec
    -0.07
    åıĹ
    -0.07
    hua
    -0.06
    LLU
    -0.06
    ream
    -0.06
    POSITIVE LOGITS
     mentioned
    0.09
     mention
    0.09
     said
    0.09
     say
    0.08
     already
    0.08
    indr
    0.08
     stated
    0.08
     mentions
    0.07
    857
    0.07
     Mention
    0.07
    Activations Density 0.008%

    No Known Activations