© 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. 72435
    Prev
    Next
    INDEX
    Explanations

    personal relationships and familial connections

    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
    Ïģο
    -0.07
    Unnamed
    -0.06
     meg
    -0.06
    _nth
    -0.06
    pared
    -0.06
    عار
    -0.06
    AtPath
    -0.06
     pregnancy
    -0.06
    <quote
    -0.06
    íļ
    -0.06
    POSITIVE LOGITS
     WWII
    0.08
    194
    0.08
     Ping
    0.08
    ivre
    0.07
     Medal
    0.07
    VIS
    0.07
    195
    0.07
     war
    0.07
     remin
    0.06
    æ¦
    0.06
    Activations Density 0.004%

    No Known Activations