© 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. 126692
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms related to names and titles

    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
    eview
    -0.09
    hled
    -0.08
    ï¼Ĭ
    -0.08
    #ad
    -0.08
     tuz
    -0.08
    .EventType
    -0.08
    quelle
    -0.07
    ctp
    -0.07
    æĪIJ人
    -0.07
     èµ·
    -0.07
    POSITIVE LOGITS
    amp
    0.06
    leet
    0.06
    âĢ¦↵
    0.06
    z
    0.06
    enade
    0.06
    820
    0.05
    âĢ¦”
    0.05
    lass
    0.05
    ijIJ
    0.05
    PARATOR
    0.05
    Activations Density 0.023%

    No Known Activations