© 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. 17-LLAMASCOPE-RES-131K
    11. 55384
    Prev
    Next
    INDEX
    Explanations

    expressions of individuality and authenticity

    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
    itra
    -0.06
    ahi
    -0.06
     Gir
    -0.06
     -
    -0.06
    -0.06
    pt
    -0.05
    PT
    -0.05
     Moran
    -0.05
     Gre
    -0.05
     Chain
    -0.05
    POSITIVE LOGITS
     authenticity
    0.10
    identity
    0.09
     Authentic
    0.09
     auth
    0.09
    .identity
    0.09
    Identity
    0.09
     natural
    0.09
     authentic
    0.08
    auth
    0.08
     identity
    0.08
    Activations Density 0.032%

    No Known Activations