© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95559
    Prev
    Next
    INDEX
    Explanations

    references to specific models or types of aircraft

    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
    uye
    -0.06
    arkin
    -0.06
    .scalablytyped
    -0.06
    grese
    -0.06
    dál
    -0.06
    NewProp
    -0.06
    arness
    -0.06
     Stein
    -0.06
     Thumbnails
    -0.06
     Fuse
    -0.06
    POSITIVE LOGITS
    _fsm
    0.07
     أش
    0.07
     destinationViewController
    0.07
     Mandatory
    0.07
    ifer
    0.07
    swer
    0.06
    çıł
    0.06
     trú
    0.06
    pekt
    0.06
    oker
    0.06
    Activations Density 0.000%

    No Known Activations