© 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. 15681
    Prev
    Next
    INDEX
    Explanations

    comparisons indicating similarity

    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
    e
    -0.06
     Weather
    -0.06
    nder
    -0.06
    ovic
    -0.06
    ke
    -0.06
    -
    -0.05
    ion
    -0.05
    o
    -0.05
    im
    -0.05
    chter
    -0.05
    POSITIVE LOGITS
     except
    0.09
    Coverage
    0.09
    Except
    0.08
    å°¼äºļ
    0.08
     concept
    0.08
    ĵåIJį
    0.08
    etto
    0.08
    //{{
    0.08
     Except
    0.08
     ÙĥØ«ÙĬر
    0.08
    Activations Density 0.018%

    No Known Activations