© 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. 5-LLAMASCOPE-RES-131K
    11. 125609
    Prev
    Next
    INDEX
    Explanations

    URLs and web links

    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
    itre
    -0.06
    ont
    -0.06
    ora
    -0.06
    avo
    -0.06
    ons
    -0.05
     dors
    -0.05
    xeb
    -0.05
    uche
    -0.05
    ady
    -0.05
    andan
    -0.05
    POSITIVE LOGITS
    fdc
    0.09
    taÅŁ
    0.08
    ;amp
    0.08
    ̣
    0.07
    celik
    0.07
    ãĥ¼ãĥ«ãĥī
    0.07
    ddb
    0.07
    burgh
    0.07
    丶
    0.07
    eyh
    0.07
    Activations Density 0.012%

    No Known Activations