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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89906
    Prev
    Next
    INDEX
    Explanations

    geographical locations and titles of nobility or leadership

    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
    anca
    -0.08
    rego
    -0.08
    antz
    -0.07
    inge
    -0.07
    иÑĤа
    -0.07
    оло
    -0.07
    ť
    -0.06
    axy
    -0.06
    pedia
    -0.06
    ritz
    -0.06
    POSITIVE LOGITS
    åħ¼
    0.07
    iddet
    0.06
     who
    0.06
     LinearGradient
    0.06
     Lester
    0.06
     whom
    0.06
    веÑĤ
    0.06
     CreateTable
    0.06
     himself
    0.06
    .scalablytyped
    0.06
    Activations Density 0.015%

    No Known Activations