© 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. 119815
    Prev
    Next
    INDEX
    Explanations

    phrases focusing on guidance and advice for job applications

    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
    bla
    -0.07
    e
    -0.06
    Wei
    -0.06
    ordan
    -0.06
    ilet
    -0.05
     Alt
    -0.05
     tone
    -0.05
    altet
    -0.05
     therefore
    -0.05
     Hat
    -0.05
    POSITIVE LOGITS
    (PHP
    0.08
    ãng
    0.07
    endon
    0.07
    ÙĨØ´
    0.07
    _UNICODE
    0.07
     racket
    0.07
    .Selenium
    0.07
    ennen
    0.07
    .metro
    0.07
    ophobic
    0.07
    Activations Density 0.012%

    No Known Activations