© 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. 16919
    Prev
    Next
    INDEX
    Explanations

    statistical terms related to household compositions and marital status

    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
    luž
    -0.08
    Ñģли
    -0.08
    CPP
    -0.07
     Uncomment
    -0.07
    ynchronously
    -0.06
     haline
    -0.06
     Hooks
    -0.06
    vier
    -0.06
     UNITY
    -0.06
    _Tis
    -0.06
    POSITIVE LOGITS
     hare
    0.07
     von
    0.06
     Scha
    0.06
    apan
    0.06
    etik
    0.06
    oken
    0.06
    emann
    0.05
     å¹³
    0.05
    ibble
    0.05
    ìł
    0.05
    Activations Density 0.000%

    No Known Activations