© 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. 76356
    Prev
    Next
    INDEX
    Explanations

    keywords related to family and significant life events

    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
    /GL
    -0.07
    .clearRect
    -0.07
    rtl
    -0.06
    çĥĪ
    -0.06
    omp
    -0.06
     gratis
    -0.06
     pillow
    -0.06
    eria
    -0.06
    hift
    -0.06
    ĥ½
    -0.06
    POSITIVE LOGITS
    abbo
    0.08
     kou
    0.07
    rogen
    0.06
    529
    0.06
     retirement
    0.06
     Hod
    0.06
     cave
    0.06
     Territory
    0.06
    ugin
    0.06
    vÄĽ
    0.06
    Activations Density 0.015%

    No Known Activations