© 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 EvalsExportsinterp-engineNEWAPI 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. 120164
    Prev
    Next
    INDEX
    Explanations

    phrases related to travel routes and connections

    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
    '=>['
    -0.07
    ona
    -0.07
    733
    -0.06
    903
    -0.06
    istrovstvÃŃ
    -0.06
     êµ
    -0.06
    uded
    -0.06
    öy
    -0.06
    .fail
    -0.06
    eyer
    -0.06
    POSITIVE LOGITS
     destinations
    0.08
    luž
    0.08
    /from
    0.08
    czy
    0.07
     destination
    0.07
     distant
    0.07
    istant
    0.06
    itus
    0.06
     London
    0.06
    destination
    0.06
    Activations Density 0.026%

    No Known Activations