© 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. 9-LLAMASCOPE-RES-131K
    11. 98221
    Prev
    Next
    INDEX
    Explanations

    references to Hawaiian culture or language

    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
    RTOS
    -0.08
    ̣
    -0.07
    fen
    -0.07
    rus
    -0.06
    ais
    -0.06
    edom
    -0.06
    éĻĨ
    -0.06
     fray
    -0.06
    increments
    -0.06
    ctr
    -0.06
    POSITIVE LOGITS
    :Object
    0.07
    úb
    0.07
     setObject
    0.06
    agna
    0.06
    llx
    0.06
    سبب
    0.06
     proven
    0.06
     Sur
    0.06
    TM
    0.06
    ellas
    0.06
    Activations Density 0.000%

    No Known Activations