© 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. 61650
    Prev
    Next
    INDEX
    Explanations

    phrases related to life milestones and transitions

    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
    úc
    -0.07
     Conc
    -0.07
    hart
    -0.07
    ite
    -0.06
    ữ
    -0.06
     Dickinson
    -0.06
     Fut
    -0.06
    izard
    -0.06
     à¤ī
    -0.06
     conc
    -0.06
    POSITIVE LOGITS
    825
    0.07
    itere
    0.06
    893
    0.06
    .Tables
    0.06
    usercontent
    0.06
    613
    0.06
    İ·
    0.06
    pios
    0.06
    ahun
    0.06
    oloj
    0.06
    Activations Density 0.011%

    No Known Activations