Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77103
    Prev
    Next
    INDEX
    Explanations

    phrases related to purchasing behavior and consumer choices

    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
    atoi
    -0.07
    znam
    -0.06
    otime
    -0.06
    Ú
    -0.06
    ync
    -0.06
    غÙĨ
    -0.06
    .CopyTo
    -0.06
    ui
    -0.06
    illet
    -0.06
    pga
    -0.06
    POSITIVE LOGITS
     other
    0.23
     another
    0.22
    another
    0.20
    åħ¶ä»ĸ
    0.18
     autre
    0.17
     otra
    0.17
     andere
    0.17
    other
    0.17
     otro
    0.17
     ëĭ¤ë¥¸
    0.17
    Activations Density 0.056%

    No Known Activations