© 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. 40517
    Prev
    Next
    INDEX
    Explanations

    aspects related to diversity and inclusivity

    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
    çļĦè¯Ŀ
    -0.08
    оÑĢоз
    -0.07
    jezd
    -0.07
    ounce
    -0.07
    caff
    -0.07
     baiser
    -0.07
    issant
    -0.07
    jf
    -0.07
    alars
    -0.07
     же
    -0.07
    POSITIVE LOGITS
    199
    0.10
    198
    0.09
    197
    0.09
    201
    0.08
    200
    0.08
    202
    0.08
    196
    0.07
    369
    0.07
    195
    0.07
    193
    0.07
    Activations Density 0.009%

    No Known Activations