© 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. 107063
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly titles and names of individuals

    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
    icie
    -0.08
    tier
    -0.07
    unce
    -0.07
    /apt
    -0.07
    alama
    -0.07
    afd
    -0.07
    aber
    -0.07
    ab
    -0.07
     Ñģклад
    -0.07
    .gnu
    -0.07
    POSITIVE LOGITS
    ptal
    0.06
    kp
    0.06
    edom
    0.05
     antagon
    0.05
    ا
    0.05
    ancel
    0.05
    Ïģα
    0.05
    è¨Ī
    0.05
    rames
    0.05
    lobby
    0.05
    Activations Density 0.019%

    No Known Activations