© 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. 95471
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and political entities

    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
    æ·¡
    -0.07
    .Submit
    -0.07
    BCM
    -0.07
    vatel
    -0.06
    WithValue
    -0.06
    æ¹
    -0.06
    _tA
    -0.06
     tet
    -0.06
    ůl
    -0.06
    ãn
    -0.06
    POSITIVE LOGITS
    wert
    0.07
     Sist
    0.06
    693
    0.06
     rum
    0.06
    105
    0.06
    lage
    0.06
    outers
    0.06
     schem
    0.06
    ans
    0.06
     Werk
    0.05
    Activations Density 0.039%

    No Known Activations