© 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. 29479
    Prev
    Next
    INDEX
    Explanations

    references to self-improvement and personal development

    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
    APH
    -0.07
    warf
    -0.07
    WER
    -0.06
    mtx
    -0.06
    inker
    -0.06
    REA
    -0.06
     Zar
    -0.06
    Refreshing
    -0.06
     cla
    -0.06
    tera
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.08
    ukan
    0.07
     hÃłnh
    0.06
    ruba
    0.06
    çħĻ
    0.06
     Gym
    0.06
     Success
    0.06
    anzi
    0.06
     insets
    0.06
    .startActivity
    0.06
    Activations Density 0.003%

    No Known Activations