© 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. 76426
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to absurdity and satire

    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
     lagi
    -0.07
    uml
    -0.07
    och
    -0.07
     parten
    -0.06
    arkin
    -0.06
    Ãłng
    -0.06
    ör
    -0.06
     respective
    -0.06
    .initial
    -0.06
    /MPL
    -0.06
    POSITIVE LOGITS
     literal
    0.07
    emet
    0.07
     potentially
    0.07
     iota
    0.06
     something
    0.06
    ExecutionContext
    0.06
    alam
    0.06
    .va
    0.06
    çĶ£
    0.06
     fucking
    0.06
    Activations Density 0.040%

    No Known Activations