© 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 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. 130965
    Prev
    Next
    INDEX
    Explanations

    dates or significant numerical 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
    .Abstractions
    -0.10
    ifu
    -0.08
    ssel
    -0.07
    minster
    -0.07
    ocab
    -0.07
    _gradients
    -0.07
    plevel
    -0.07
    stit
    -0.07
    umont
    -0.07
     befind
    -0.07
    POSITIVE LOGITS
     birthday
    0.06
     flor
    0.06
    strup
    0.06
    AutoSize
    0.05
    ;
    0.05
     {
    0.05
     birthdays
    0.05
     birth
    0.05
     tw
    0.05
    onte
    0.05
    Activations Density 0.000%

    No Known Activations