© 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. 126521
    Prev
    Next
    INDEX
    Explanations

    structural elements and components related to web or application forms and layouts

    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
    urette
    -0.07
    angl
    -0.06
    aryl
    -0.06
    engl
    -0.06
    stadt
    -0.06
    Ìģc
    -0.06
     frau
    -0.06
    olor
    -0.06
     ******************************************************************************↵
    -0.06
    andre
    -0.06
    POSITIVE LOGITS
    SetBranch
    0.07
    ãĢĤãĢĤ↵↵
    0.07
     elt
    0.07
    )((((
    0.06
    enderror
    0.06
    isContained
    0.06
    âĢĮâĢĮ
    0.06
    printStats
    0.06
    FindObject
    0.06
    .RunWith
    0.06
    Activations Density 0.055%

    No Known Activations