© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 41948
    Prev
    Next
    INDEX
    Explanations

    phrases related to the emergence and existence of entities or concepts from non-existence

    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
    ong
    -0.07
    208
    -0.06
    rie
    -0.06
     åĪ¶
    -0.06
    eding
    -0.06
     onSave
    -0.06
    urer
    -0.06
     enumer
    -0.06
    asan
    -0.06
    iske
    -0.06
    POSITIVE LOGITS
    _magic
    0.08
     magic
    0.08
     sudden
    0.07
     nowhere
    0.07
    çªģçĦ¶
    0.07
     suddenly
    0.07
    FROM
    0.07
    .sprites
    0.07
    èĽ
    0.07
     Magic
    0.06
    Activations Density 0.055%

    No Known Activations