© 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. 125547
    Prev
    Next
    INDEX
    Explanations

    the names of famous authors, particularly in the context of their contributions to literature

    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
    ods
    -0.06
    werk
    -0.06
    ose
    -0.06
    ore
    -0.05
    848
    -0.05
    anted
    -0.05
     charismatic
    -0.05
     Briggs
    -0.05
     forth
    -0.05
    anth
    -0.05
    POSITIVE LOGITS
     nouve
    0.08
    ıģ
    0.07
    /gpl
    0.07
    clamp
    0.07
     Sabha
    0.07
    pga
    0.07
    0.07
    roti
    0.07
    Uniform
    0.07
    .mybatisplus
    0.07
    Activations Density 0.000%

    No Known Activations