© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 61322
    Prev
    Next
    INDEX
    Explanations

    phrases indicating training or education standards

    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
    geist
    -0.09
    rek
    -0.07
    ocab
    -0.07
    ër
    -0.07
    afort
    -0.07
    eing
    -0.07
     itself
    -0.07
    atica
    -0.07
    okens
    -0.06
    asant
    -0.06
    POSITIVE LOGITS
    /lic
    0.08
    amburger
    0.06
    sville
    0.06
     barr
    0.06
     ZEND
    0.06
     to
    0.06
     <",
    0.06
    леÑĤ
    0.06
     vers
    0.06
    eman
    0.06
    Activations Density 0.009%

    No Known Activations