© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 678
    Prev
    Next
    INDEX
    Explanations

    expressions of familial connection and personal reflections on parenting

    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
    лекÑģанд
    -0.09
    ursal
    -0.09
    vrier
    -0.09
    åĪ«
    -0.08
    upos
    -0.08
    abit
    -0.08
    ALSE
    -0.08
    onical
    -0.08
    ecess
    -0.07
    oupper
    -0.07
    POSITIVE LOGITS
     paren
    0.06
     love
    0.06
     tend
    0.06
     child
    0.06
     Sass
    0.06
     biological
    0.06
     loving
    0.06
    575
    0.06
     
    0.05
    hlen
    0.05
    Activations Density 0.051%

    No Known Activations