© 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. 74913
    Prev
    Next
    INDEX
    Explanations

    references to historical reports and context surrounding crafts and their societal implications

    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
    алеж
    -0.08
    вок
    -0.07
    Disclosure
    -0.07
    Multiplicity
    -0.07
    Trivia
    -0.07
    ationship
    -0.07
    zem
    -0.07
    htdocs
    -0.07
     Leer
    -0.06
    nod
    -0.06
    POSITIVE LOGITS
     report
    0.11
     descriptions
    0.10
     description
    0.10
     reports
    0.10
     records
    0.09
     contemporary
    0.09
     reported
    0.09
     describe
    0.09
     Description
    0.09
     recorded
    0.09
    Activations Density 0.087%

    No Known Activations