© 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. 15-LLAMASCOPE-RES-131K
    11. 90450
    Prev
    Next
    INDEX
    Explanations

    data related to neonatal care and statistics

    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
    ãĥĬãĥ«
    -0.08
     desp
    -0.07
    aticon
    -0.07
    åIJĽ
    -0.07
    ãĤĤãģĨ
    -0.07
    ãĢģãģ©ãģĨ
    -0.07
     Incontri
    -0.07
    enet
    -0.07
    eniable
    -0.06
    ationToken
    -0.06
    POSITIVE LOGITS
     rate
    0.07
     rates
    0.07
     death
    0.07
    rate
    0.07
     Ces
    0.06
    áºŃp
    0.06
    rates
    0.06
     baby
    0.06
    recht
    0.06
     child
    0.06
    Activations Density 0.003%

    No Known Activations