© 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. 84077
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and research publications

    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
    049
    -0.06
    emon
    -0.05
    unami
    -0.05
    òng
    -0.05
     surre
    -0.05
    ź
    -0.05
     Kaynak
    -0.05
    976
    -0.05
    _io
    -0.05
    udios
    -0.05
    POSITIVE LOGITS
     published
    0.11
     publish
    0.10
     publishes
    0.09
    _publish
    0.09
    .publish
    0.09
     publishing
    0.09
    published
    0.09
     publication
    0.09
    .published
    0.08
    Publish
    0.08
    Activations Density 0.008%

    No Known Activations