© 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. 74476
    Prev
    Next
    INDEX
    Explanations

    phrases describing mathematical or scientific models and their representations

    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
    uci
    -0.07
    pte
    -0.07
    fusc
    -0.06
    emez
    -0.06
    Dims
    -0.06
    DISPLAY
    -0.06
     gib
    -0.06
    ffa
    -0.06
     verd
    -0.06
    avit
    -0.06
    POSITIVE LOGITS
    ÙĦاÙĦ
    0.07
    иÑĤов
    0.07
    æµľ
    0.06
    ogo
    0.06
     simplement
    0.06
    APPED
    0.06
     æĵ
    0.06
    ãģĦãģĨ
    0.06
     using
    0.06
    probe
    0.06
    Activations Density 0.035%

    No Known Activations