© 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. 22-LLAMASCOPE-RES-131K
    11. 3776
    Prev
    Next
    INDEX
    Explanations

    date and timestamp information

    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
    posted
    -0.07
    ieur
    -0.06
    ef
    -0.06
    è£Ĥ
    -0.06
    uce
    -0.06
    ække
    -0.06
    incip
    -0.06
    anan
    -0.06
    orate
    -0.06
    omencl
    -0.06
    POSITIVE LOGITS
    841
    0.07
    (java
    0.06
     MAL
    0.06
     Irvine
    0.06
    alon
    0.06
    .scalablytyped
    0.06
    à¹Ĥà¸ķ
    0.06
    ombok
    0.06
    ī
    0.06
    .rl
    0.06
    Activations Density 0.003%

    No Known Activations