© 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. 117396
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of belonging or 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
    Å¡ak
    -0.07
    zn
    -0.07
    bage
    -0.07
    olv
    -0.07
    inja
    -0.07
    ÏĢÏĮ
    -0.07
    (#
    -0.07
    nex
    -0.06
    á»ĭp
    -0.06
    .scalablytyped
    -0.06
    POSITIVE LOGITS
    agram
    0.07
     whom
    0.07
     stature
    0.06
     integrity
    0.06
     transit
    0.06
    orca
    0.05
    WEB
    0.05
    anske
    0.05
    assel
    0.05
     cloth
    0.05
    Activations Density 0.005%

    No Known Activations