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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43589
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and their contributions

    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
    ocracy
    -0.07
    ekl
    -0.06
     einzel
    -0.06
    _processors
    -0.06
    istrovstvÃŃ
    -0.06
    woman
    -0.06
    getMock
    -0.06
    oner
    -0.06
     erót
    -0.06
    imap
    -0.05
    POSITIVE LOGITS
     who
    0.24
     whom
    0.23
    who
    0.21
     himself
    0.18
     whose
    0.18
    whose
    0.15
     Jr
    0.15
     quien
    0.14
     grandson
    0.12
     son
    0.12
    Activations Density 0.076%

    No Known Activations