© 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 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. 17-LLAMASCOPE-RES-131K
    11. 87413
    Prev
    Next
    INDEX
    Explanations

    phrases related to individuality and self-identity

    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
    lauf
    -0.07
    nze
    -0.07
    agli
    -0.07
    usher
    -0.07
    eor
    -0.06
    noinspection
    -0.06
    à¸Ńà¸Ķ
    -0.06
    onden
    -0.06
    ampus
    -0.06
    gende
    -0.06
    POSITIVE LOGITS
    Deque
    0.06
     benef
    0.06
     Nobody
    0.06
    ël
    0.06
     satisf
    0.05
     Robert
    0.05
    ibia
    0.05
     coer
    0.05
    ipop
    0.05
     Glover
    0.05
    Activations Density 0.010%

    No Known Activations