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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 90676
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of uniqueness or singularity in relation to experiences or resources

    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
    öt
    -0.08
     Fond
    -0.06
     Gur
    -0.06
    imoto
    -0.06
    _display
    -0.06
     Tran
    -0.05
     "
    -0.05
     Eig
    -0.05
    -display
    -0.05
     analyst
    -0.05
    POSITIVE LOGITS
    #ac
    0.09
    chedulers
    0.08
    enstein
    0.08
    ervlet
    0.08
    SCII
    0.07
    ernes
    0.07
    ernals
    0.07
    еÑĢк
    0.07
    OperationException
    0.07
    _TAC
    0.07
    Activations Density 0.001%

    No Known Activations