© 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. 54454
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and URLs associated with individuals or websites

    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
    .appspot
    -0.09
    anon
    -0.08
    jedn
    -0.08
    Unnamed
    -0.07
    abler
    -0.07
    emez
    -0.07
    sak
    -0.07
     ourselves
    -0.07
    #ga
    -0.07
    åIJįçĦ¡ãģĹãģķãĤĵ
    -0.07
    POSITIVE LOGITS
    ye
    0.07
    @dynamic
    0.06
    istrovstvÃŃ
    0.06
    iform
    0.06
    ئ
    0.06
     ÑĢай
    0.06
    å¼ı
    0.06
     prov
    0.06
     wom
    0.06
    onth
    0.05
    Activations Density 0.013%

    No Known Activations