© 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. 60096
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Seks
    -0.09
    .ci
    -0.07
    лади
    -0.07
    ,www
    -0.07
    LOTS
    -0.07
    linger
    -0.07
    ahl
    -0.07
    endor
    -0.07
    TEMPL
    -0.07
    ÅĤu
    -0.07
    POSITIVE LOGITS
    202
    0.07
     vener
    0.07
     reluct
    0.06
     canceled
    0.06
     inflation
    0.06
     Greenwood
    0.06
     âģ
    0.05
     arch
    0.05
    onium
    0.05
     COVID
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.