© 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. 41191
    Prev
    Next
    INDEX
    Explanations

    structured data representation in code

    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
    ξι
    -0.09
     داÙħ
    -0.08
    anax
    -0.08
     yourselves
    -0.07
    alars
    -0.07
    .SEVER
    -0.07
    AAAA
    -0.07
    abler
    -0.07
    æĿī
    -0.07
    viously
    -0.07
    POSITIVE LOGITS
     age
    0.11
     birth
    0.10
     Age
    0.08
    age
    0.08
    birth
    0.08
    (age
    0.07
     ages
    0.07
    身
    0.07
     Birth
    0.07
    .age
    0.07
    Activations Density 0.012%

    No Known Activations