© 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. 90055
    Prev
    Next
    INDEX
    Explanations

    elements related to personal growth and development journeys

    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
     late
    -0.07
    reh
    -0.06
    rı
    -0.06
    ungan
    -0.06
    rente
    -0.06
    Ymd
    -0.06
     Late
    -0.06
    asp
    -0.06
    <<<
    -0.06
    eyen
    -0.06
    POSITIVE LOGITS
    åħĪ
    0.16
     first
    0.15
     before
    0.15
     먼ìłĢ
    0.15
    first
    0.15
    먼
    0.14
     åħĪ
    0.14
    before
    0.13
    -before
    0.12
     antes
    0.12
    Activations Density 0.149%

    No Known Activations