© 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. 58816
    Prev
    Next
    INDEX
    Explanations

    content related to environmental sustainability and responsible consumer behavior

    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
    hend
    -0.09
    .Please
    -0.08
    lsi
    -0.08
    unger
    -0.08
     )↵↵↵↵↵↵↵↵
    -0.08
    itle
    -0.07
    inue
    -0.07
    epar
    -0.07
    uts
    -0.07
    bourg
    -0.07
    POSITIVE LOGITS
     *,
    0.05
     STAT
    0.05
     incon
    0.05
    ;
    0.05
    328
    0.05
     اض
    0.05
     sometimes
    0.05
     perhaps
    0.05
    è¦
    0.05
     inconvenient
    0.05
    Activations Density 0.153%

    No Known Activations