© 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. 1098
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal priorities and spiritual practices

    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
    ...↵
    -0.06
    -0.06
     exhaust
    -0.06
     exhausted
    -0.05
     sw
    -0.05
    erb
    -0.05
    u
    -0.05
    ุล
    -0.05
     AU
    -0.05
     cul
    -0.05
    POSITIVE LOGITS
     habit
    0.11
     habits
    0.10
    habit
    0.09
     Habit
    0.09
    _OW
    0.08
    [port
    0.08
     cigaret
    0.08
     daily
    0.08
    hab
    0.08
    redential
    0.08
    Activations Density 0.013%

    No Known Activations