© 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. 128883
    Prev
    Next
    INDEX
    Explanations

    names of individuals and organizations in various contexts

    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
    anca
    -0.07
    zon
    -0.07
     McGu
    -0.07
    .dw
    -0.07
    anium
    -0.07
    ï¸
    -0.07
    eba
    -0.07
    ÑĤÑĢа
    -0.07
    ÏĢιÏĥ
    -0.07
    atos
    -0.06
    POSITIVE LOGITS
    æīĢ
    0.07
    857
    0.07
     æīĢ
    0.07
     say
    0.06
    pedia
    0.06
    695
    0.06
    swire
    0.06
     sa
    0.06
     pointed
    0.06
    pers
    0.05
    Activations Density 0.016%

    No Known Activations