© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 88069
    Prev
    Next
    INDEX
    Explanations

    the name "Matthew" in various contexts

    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
    notated
    -0.08
    ëij¥
    -0.07
    uet
    -0.07
    ContentLoaded
    -0.07
    .Cryptography
    -0.07
    oir
    -0.07
    ardu
    -0.07
    ÐIJÑĢÑħÑĸв
    -0.07
    nun
    -0.07
    ELY
    -0.07
    POSITIVE LOGITS
    mania
    0.09
    rex
    0.08
    ings
    0.08
    son
    0.08
    resses
    0.07
    opia
    0.07
    raj
    0.07
    ij
    0.07
    ews
    0.07
    sonian
    0.07
    Activations Density 0.008%

    No Known Activations