© 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. 9-LLAMASCOPE-RES-131K
    11. 97795
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to lists and categorization

    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
    zzo
    -0.06
    rosse
    -0.05
    rescia
    -0.05
    λλα
    -0.05
     McK
    -0.05
    itung
    -0.05
    ateg
    -0.05
    se
    -0.05
    eza
    -0.05
    otlin
    -0.05
    POSITIVE LOGITS
    º
    0.08
    -toggler
    0.07
    INCT
    0.07
     tiener
    0.07
    aris
    0.07
    olib
    0.07
    ró
    0.07
    «a
    0.07
     Stars
    0.07
    éģĵ
    0.07
    Activations Density 0.001%

    No Known Activations