© 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. 9-LLAMASCOPE-RES-131K
    11. 95601
    Prev
    Next
    INDEX
    Explanations

    instances of passive voice or reports of past actions

    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
    ariat
    -0.06
    inspace
    -0.06
    管
    -0.06
     mau
    -0.06
    nees
    -0.06
    ari
    -0.06
     ing
    -0.06
    .synthetic
    -0.05
    ire
    -0.05
    640
    -0.05
    POSITIVE LOGITS
    cela
    0.09
    ãĥ¼ãĥĭ
    0.07
    ãģ£ãģı
    0.07
    'gc
    0.07
    اباÙĨ
    0.06
     خاص
    0.06
    ozem
    0.06
    unsch
    0.06
    มาย
    0.06
    ì§Ī
    0.06
    Activations Density 0.034%

    No Known Activations