© 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. 17-LLAMASCOPE-RES-131K
    6. 40304
    Prev
    Next
    INDEX
    Explanations

    phrases related to preservation or redemption

    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
     nobody
    -0.06
    kou
    -0.06
     fractional
    -0.06
    pei
    -0.06
    dz
    -0.06
    :CGRect
    -0.06
     Perception
    -0.06
     ("
    -0.05
     abdomen
    -0.05
    'u
    -0.05
    POSITIVE LOGITS
    меÑĩ
    0.08
    launcher
    0.07
    mix
    0.07
    ichten
    0.07
     addCriterion
    0.07
    ÑĭÑĤ
    0.07
    .walk
    0.07
    izmet
    0.07
     Barney
    0.06
    ÛĮدÙĨ
    0.06
    Activations Density 0.000%

    No Known Activations