© 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. 5-LLAMASCOPE-RES-131K
    11. 126528
    Prev
    Next
    INDEX
    Explanations

    terms related to student loans and financial assistance programs

    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
     bilder
    -0.07
     noreferrer
    -0.07
    thinkable
    -0.07
    thes
    -0.06
    oval
    -0.06
    zers
    -0.06
    orton
    -0.06
     Nisan
    -0.06
     Haskell
    -0.06
    dehy
    -0.06
    POSITIVE LOGITS
    uche
    0.07
     Jefferson
    0.07
    æĭĶ
    0.06
    iche
    0.06
    åįļ
    0.06
    529
    0.06
    obili
    0.06
    otos
    0.06
    914
    0.06
    jian
    0.06
    Activations Density 0.235%

    No Known Activations