Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95948
    Prev
    Next
    INDEX
    Explanations

    expressions of introspection and personal reflection

    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
    tro
    -0.07
     Troy
    -0.06
    ħ
    -0.06
     tro
    -0.06
    _PB
    -0.06
    stor
    -0.06
    Tro
    -0.06
    ä¸ļ
    -0.06
    arat
    -0.06
    jer
    -0.06
    POSITIVE LOGITS
    ëĭ
    0.07
    velt
    0.06
     Immutable
    0.06
    alace
    0.06
    elpers
    0.06
     JsonSerializer
    0.06
    ayah
    0.06
     tunnel
    0.06
    Nice
    0.06
    dge
    0.06
    Activations Density 0.015%

    No Known Activations