© 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. 88493
    Prev
    Next
    INDEX
    Explanations

    themes related to identity and cultural experience

    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
    ajas
    -0.08
    hardt
    -0.07
    IfExists
    -0.07
     ruku
    -0.06
    iveau
    -0.06
     Fasc
    -0.06
    æİĪ
    -0.06
    deliver
    -0.06
    ammen
    -0.06
    xes
    -0.06
    POSITIVE LOGITS
     identity
    0.10
    identity
    0.09
     Identity
    0.09
    Identity
    0.08
     hy
    0.08
    身份
    0.08
    _identity
    0.07
     identities
    0.07
    316
    0.07
     dias
    0.06
    Activations Density 0.039%

    No Known Activations