© 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 EvalsExportsinterp-engineNEWAPI 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. 54159
    Prev
    Next
    INDEX
    Explanations

    terms related to color and visual characteristics

    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
    portlet
    -0.08
    rok
    -0.07
    PÅĻi
    -0.07
    aned
    -0.07
    jmp
    -0.07
    onical
    -0.07
    oro
    -0.07
    _ASSUME
    -0.07
    ANGED
    -0.07
    agens
    -0.07
    POSITIVE LOGITS
    ateria
    0.06
     Bailey
    0.06
    aux
    0.05
    ł
    0.05
    ogn
    0.05
     sta
    0.05
    ilia
    0.05
     viz
    0.05
    225
    0.05
    .infinity
    0.05
    Activations Density 0.110%

    No Known Activations