© 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. 77298
    Prev
    Next
    INDEX
    Explanations

    instances of politically charged statements or events

    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
     according
    -0.07
    çı
    -0.06
    OPS
    -0.06
    ÙģÙĩ
    -0.06
    ÐŀÐł
    -0.06
    ña
    -0.06
    according
    -0.06
    iper
    -0.06
    WORD
    -0.06
    ellas
    -0.06
    POSITIVE LOGITS
    esktop
    0.07
    /REC
    0.06
    andom
    0.06
    /my
    0.06
     no
    0.06
     kata
    0.06
    urer
    0.06
     rám
    0.06
    yles
    0.06
     don
    0.06
    Activations Density 0.012%

    No Known Activations